Quick links: By date / By type / By project / By topic / Award winning / Recent docs / Recent talks / Scholar / dblp /

Project huawei newnet mplane smartuc connect napa trans tiger other

Huawei 45

• [CoNEXT-NNI-22a] Boffa, Matteo and Vassio, Luca and Drago, Idilio and Mellia, Marco and Milan, Giulia and Houidi, Zied Ben and Rossi, Dario, "On Using Pretext Tasks to Learn Representations from Network Logs" ACM CoNext workshop on Native Network Intelligence (NNI) dec. 2022, Conference Abstract Bibtex

  @inproceedings{DR:CoNEXT-NNI-22a,
    title = {{On Using Pretext Tasks to Learn Representations from Network Logs}},
    author = {Boffa, Matteo and Vassio, Luca and Drago, Idilio and Mellia, Marco and Milan, Giulia and Houidi, Zied Ben and Rossi, Dario},
    year = {2022},
    month = dec,
    topic = {network-security},
    booktitle = {ACM CoNext workshop on Native Network Intelligence (NNI)},
    howpublished = {https://nonsns.github.io/paper/rossi22conext-nni-a.pdf}
  }
  

  Learning meaningful representations from network data is critical to ease the adoption of AI as a cornerstone to process network logs. Since a large portion of such data is textual, Natural Language Processing (NLP) appears as an obvious candidate to learn their representations. Indeed, the literature proposes impressive applications of NLP applied to textual network data. However, in the absence of labels, objectively evaluating the goodness of the learned representations is still an open problem. We call for a systematic adoption of domain-specific pretext tasks to select the best representation from network data. Relying on such tasks enables us to evaluate different representations on side machine learning problems and, ultimately, unveiling the best candidate representations for the more interesting downstream tasks for which labels are scarce or unavailable. We apply pretext tasks in the analysis of logs collected from SSH honeypots. Here, a cumbersome downstream task is to cluster events that exhibit a similar attack pattern. We propose the following pipeline: first, we represent the input data using a classic NLP-based approach. Then, we design pretext tasks to objectively evaluate the representation goodness and to select the best one. Finally, we use the best representation to solve the unsupervised task, which uncovers interesting behaviours and attack patterns. All in all, our proposal can be generalized to other text-based network logs beyond honeypots.
• [CoNEXT-NNI-22b] Rossi, Dario and Liang, Zhang, "Native Network Intelligence, Fast and Slow" ACM CoNext workshop on Native Network Intelligence (NNI) dec. 2022, Conference Abstract Bibtex

  @inproceedings{DR:CoNEXT-NNI-22b,
    title = {{Native Network Intelligence, Fast and Slow}},
    author = {Rossi, Dario and Liang, Zhang},
    year = {2022},
    month = dec,
    topic = {ai-native},
    booktitle = {ACM CoNext workshop on Native Network Intelligence (NNI)},
    howpublished = {https://nonsns.github.io/paper/rossi22conext-nni-b.pdf}
  }
  

  As networks have historically been built around connectivity, architectural features concerning quality of service, mobility, security and privacy have been added as afterthoughts – with consequent well known architectural headaches for their later integration. Despite Artificial Intelligence (AI) is more a means to an end, that an architectural feature itself, this is not completely different from what concerns its integration: in particular, while Cloud and Edge computing paradigms made it possible to use AI techniques to relieve part of network operation, however AI is currently little more than an additional tool. This paper describes a vision of future networks, where AI becomes a first class commodity: its founding principle lays around the concept of “fast and slow” type of AI reasoning, each of which offers different types of AI capabilities to process network data. We next outline how these building blocks naturally maps to different network segments, and discuss emerging AI-to-AI communication patterns as we move to more intelligent networks.
• [CoNEXT-GNN-22] Fernandes, Danilo Marinho and Krolikowski, Jonatan and Houidi, Zied Ben and Chen, Fuxing and Rossi, Dario, "Cross-network transferable neural models for WLAN interference estimation" ACM CoNext workshop on Graph Neural Networks (GNN) dec. 2022, Conference Abstract Bibtex

  @inproceedings{DR:CoNEXT-GNN-22,
    title = {{Cross-network transferable neural models for WLAN interference estimation}},
    author = {Fernandes, Danilo Marinho and Krolikowski, Jonatan and Houidi, Zied Ben and Chen, Fuxing and Rossi, Dario},
    year = {2022},
    month = dec,
    booktitle = {ACM CoNext workshop on Graph Neural Networks (GNN)},
    topic = {wlan},
    howpublished = {https://nonsns.github.io/paper/rossi22conext-gnn.pdf}
  }
  

  Airtime interference is a key performance indicator for WLANs, measuring, for a given time period, the percentage of time during which a node is forced to wait for other transmissions before to transmitting or receiving. Being able to accurately estimate interference resulting from a given state change (e.g., channel, bandwidth, power) would allow a better control of WLAN resources, assessing the impact of a given configuration before actually implementing it. In this paper, we adopt a principled approach to interference estimation in WLANs. We first use real data to characterize the factors that impact it, and derive a set of relevant synthetic workloads for a controlled comparison of various deep learning architectures in terms of accuracy, generalization and robustness to outlier data. We find, unsurprisingly, that Graph Convolutional Networks (GCNs) yield the best performance overall, leveraging the graph structure inherent to campus WLANs. We notice that, unlike e.g. LSTMs, they struggle to learn the behavior of specific nodes, unless given the node indexes in addition. We finally verify GCN model generalization capabilities, by applying trained models on operational deployments unseen at training time.
• [CommMag-22] Iacoboaiea, Ovidiu and Krolikowski, Jonatan and Houidi, Zied Ben and Rossi, Dario, "From Design to Deployment of Zero-touch Deep Reinforcement Learning WLANs" In IEEE Communications Magazine (vol. to appear), dec. 2022, DOI 10.1109/MCOM.002.2200318 arXiv Journal Abstract Bibtex

  @article{DR:CommMag-22,
    author = {Iacoboaiea, Ovidiu and Krolikowski, Jonatan and Houidi, Zied Ben and Rossi, Dario},
    title = {From Design to Deployment of Zero-touch Deep Reinforcement Learning WLANs},
    arxiv = {https://arxiv.org/abs/2207.06172},
    journal = {IEEE Communications Magazine (vol. to appear)},
    year = {2022},
    month = dec,
    doi = {10.1109/MCOM.002.2200318},
    howpublished = {/ai4net/docs/rossi22commag.pdf},
    topic = {wlan}
  }
  

  Machine learning (ML) is increasingly used to automate networking tasks, in a paradigm known as zero-touch network and service management (ZSM). In particular, Deep Reinforcement Learning (DRL) techniques have recently gathered much attention for their ability to learn taking complex decisions in different fields. In the ZSM context, DRL is an appealing candidate for tasks such as dynamic resource allocation, that is generally formulated as hard optimization problems. At the same time, successful training and deployment of DRL agents in real-world scenarios faces a number of challenges that we outline and address in this paper. Tackling the case of Wireless Local Area Network (WLAN) radio resource management, we report guidelines that extend to other usecases and more general contexts.
• [AICCSA-22] Nesic, Stefan and Putina, Andrian and Bahri, Maroua and Huet, Alexis and Navarro, Jose Manuel and Rossi, Dario and Sozio, Mauro, "StreamRHF: Tree-based unsupervised anomaly detection for data streams" 19th ACS/IEEE International Conference on Computer Systems and Applications (AICCSA 2022) dec. 2022, Conference Abstract Bibtex

  @inproceedings{DR:AICCSA-22,
    title = {{StreamRHF: Tree-based unsupervised anomaly detection for data streams}},
    author = {Nesic, Stefan and Putina, Andrian and Bahri, Maroua and Huet, Alexis and Navarro, Jose Manuel and Rossi, Dario and Sozio, Mauro},
    year = {2022},
    month = dec,
    booktitle = {19th ACS/IEEE International Conference on Computer Systems and Applications (AICCSA 2022)},
    howpublished = {https://nonsns.github.io/paper/rossi22aiccsa.pdf},
    topic = {ad-algo}
  }
  

  We present StreamRHF, an unsupervised anomaly detection algorithm for data streams. Our algorithm builds on some of the ideas of Random Histogram Forest (RHF), a state-of-the-art algorithm for batch unsupervised anomaly detection. StreamRHF constructs a forest of decision trees, where feature splits are determined according to the kurtosis score of every feature. It irrevocably assigns an anomaly score to data points, as soon as they arrive, by means of an incremental computation of its random trees and the kurtosis scores of the features. This allows efficient online scoring and concept drift detection altogether. Our approach is tree-based which boasts several appealing properties, such as explainability of the results. We conduct an extensive experimental evaluation on multiple datasets from different real-world applications. Our evaluation shows that our streaming algorithm achieves comparable average precision to RHF while outperforming state-of-the-art streaming approaches for unsupervised anomaly detection with furthermore limited computational complexity.
• [HotNets-22] Houidi, Zied Ben and Azorin, Raphael and Gallo, Massimo and Finamore, Alessandro and Rossi, Dario, "Towards a systematic multi-modal representation learning for network data" ACM HotNets nov. 2022, Conference Abstract Bibtex

  @inproceedings{DR:HotNets-22,
    title = {{Towards a systematic multi-modal representation learning for network data}},
    author = {Houidi, Zied Ben and Azorin, Raphael and Gallo, Massimo and Finamore, Alessandro and Rossi, Dario},
    year = {2022},
    month = nov,
    booktitle = {ACM HotNets},
    howpublished = {https://nonsns.github.io/paper/rossi22hotnets.pdf},
    topic = {ai-native}
  }
  

  Learning the right representations from complex input data is the key ability of successful machine learning (ML) models. The latter are often tailored to a specific data modality. For example, recurrent neural networks (RNNs) were designed having the processing of sequential data in mind, while convolutional neural networks (CNNs) were designed to exploit spatial correlation naturally present in images. Unlike computer vision (CV) and natural language processing (NLP), each of which targets a single well-defined modality, network ML problems often have a mixture of data modalities as input. Yet, instead of exploiting such abundance, practitioners tend to rely on sub-features thereof, reducing the problem on single modality for the sake of simplicity. In this paper, we advocate for exploiting all the modalities naturally present in network data. As a first step, we observe that network data systematically exhibits a mixture of quantities (e.g., measurements), and entities (e.g., IP addresses, names, etc.). Whereas the former are generally well exploited, the latter are often underused or poorly represented (e.g., with one-hot encoding). We propose to systematically leverage state of the art embedding techniques to learn entity representations, whenever significant sequences of such entities are historically observed. Through two diverse usecases, we show that such entity encoding can benefit and naturally augment classic quantity-based features.
• [ComNet-22] Navarro, Jose Manuel and Huet, Alexis and Rossi, Dario, "Human readable network troubleshooting based on anomaly detection and feature scoring" nov. 2022, DOI https://doi.org/10.1016/j.comnet.2022.109447 arXiv Tech.Rep. Abstract Bibtex

  @techreport{DR:ComNet-22,
    title = {Human readable network troubleshooting based on anomaly detection and feature scoring},
    author = {Navarro, Jose Manuel and Huet, Alexis and Rossi, Dario},
    journal = {Elsevier Computer Networks},
    month = nov,
    volume = {219},
    year = {2022},
    issn = {1389-1286},
    topic = {ad-fs},
    doi = {https://doi.org/10.1016/j.comnet.2022.109447},
    arxiv = {https://arxiv.org/abs/2108.11807},
    howpublished = {}
  }
  

  Network troubleshooting is still a heavily human-intensive process. To reduce the time spent by human operators in the diagnosis process, we present a system based on (i) unsupervised learning methods for detecting anomalies in the time domain, (ii) an attention mechanism to rank features in the feature space and finally (iii) an expert knowledge module able to seamlessly incorporate previously collected domain-knowledge. In this paper, we thoroughly evaluate the performance of the full system and of its individual building blocks: particularly, we consider (i) 10 anomaly detection algorithms as well as (ii) 10 attention mechanisms, that comprehensively represent the current state of the art in the respective fields. Leveraging a unique collection of expert-labeled datasets worth several months of real router telemetry data, we perform a thorough performance evaluation contrasting practical results in constrained stream-mode settings, with the results achievable by an ideal oracle in academic settings. Our experimental evaluation shows that (i) the proposed system is effective in achieving high levels of agreement with the expert, and (ii) that even a simple statistical approach is able to extract useful information from expert knowledge gained in past cases, significantly improving troubleshooting performance.
• [TNSM-22] Rossi, Dario and Zhang, Liang, "Landing AI on Networks: An equipment vendor viewpoint on Autonomous Driving Networks" In IEEE Transactions on Network and Service Management (TNSM), Vol. 19, sep. 2022, DOI 10.1109/TNSM.2022.3169988 arXiv Journal Abstract Bibtex

  @article{DR:TNSM-22,
    title = {Landing AI on Networks: An equipment vendor viewpoint on Autonomous Driving Networks},
    author = {Rossi, Dario and Zhang, Liang},
    month = sep,
    volume = {19},
    issue = {3},
    year = {2022},
    journal = {IEEE Transactions on Network and Service Management (TNSM)},
    doi = {10.1109/TNSM.2022.3169988},
    howpublished = {https://nonsns.github.io/paper/rossi22tnsm.pdf},
    arxiv = {https://arxiv.org/abs/2205.08347},
    topic = {ai-native}
  }
  

  The tremendous achievements of Artificial Intelligence (AI) in computer vision, natural language processing, games and robotics, has extended the reach of the AI hype to other fields: in telecommunication networks, the long term vision is to let AI fully manage, and autonomously drive, all aspects of network operation. In this industry vision paper, we discuss challenges and opportunities of Autonomous Driving Network (ADN) driven by AI technologies. To understand how AI can be successfully landed in current and future networks, we start by outlining challenges that are specific to the networking domain, putting them in perspective with advances that AI has achieved in other fields. We then present a system view, clarifying how AI can be fitted in the network architecture. We finally discuss current achievements as well as future promises of AI in networks, mentioning roadmap to avoid bumps in the road that leads to true large-scale deployment of AI technologies in network
• [ITC-22] Navarro, Jose Manuel and Huet, Alexis and Rossi, Dario, "Rare Yet Popular: Evidence and Implications from Anomaly Detection Datasets" International Teletraffic Congress (ITC34) sep. 2022, arXiv Conference Abstract Bibtex

  @inproceedings{DR:ITC-22,
    title = {Rare Yet Popular: Evidence and Implications from Anomaly Detection Datasets},
    author = {Navarro, Jose Manuel and Huet, Alexis and Rossi, Dario},
    month = sep,
    year = {2022},
    booktitle = {International Teletraffic Congress (ITC34)},
    howpublished = {https://nonsns.github.io/paper/rossi22itc.pdf},
    arxiv = {https://arxiv.org/abs/2211.10129},
    topic = {ad-fs}
  }
  

  Anomaly detection research works generally propose algorithms or end-to-end systems that are designed to automatically discover outliers in a dataset or a stream. While literature abounds concerning algorithms or the definition of metrics for better evaluation, the quality of the ground truth against which they are evaluated is seldom questioned. On this paper, we present a systematic analysis of available public (and additionally our private) ground truth for anomaly detection in the context of network environment, where data is intrinsically temporal, multivariate and, in particular, exhibits spatial properties, which to the best of our knowledge we are the first to explore. Our analysis reveals that, while anomalies are by definition temporally rare events, their spatial characterization clearly shows some type of anomalies are significantly more popular than others. This can be achieved through surprisingly simple techniques and may have profound implications on the cost and quality of the labeling process.
• [ComCom-22] Houidi, Zied Ben and Rossi, Dario, "Neural language models for network configuration: Opportunities and reality check" In Elsevier Computer Communication, Vol. (to appear), pp.Pages 118-125, sep. 2022, DOI https://doi.org/10.1016/j.comcom.2022.06.035 arXiv Journal Abstract Bibtex

  @article{DR:ComCom-22,
    title = {Neural language models for network configuration: Opportunities and reality check},
    author = {Houidi, Zied Ben and Rossi, Dario},
    month = sep,
    issue = {193},
    pages = {Pages 118-125},
    year = {2022},
    journal = {Elsevier Computer Communication},
    volume = {(to appear)},
    howpublished = {https://nonsns.github.io/paper/rossi22comcom.pdf},
    doi = {https://doi.org/10.1016/j.comcom.2022.06.035},
    arxiv = {https://arxiv.org/abs/2205.01398},
    topic = {ai-native}
  }
  

  Boosted by deep learning, natural language processing (NLP) techniques have recently seen spectacular progress, mainly fueled by breakthroughs both in representation learning with word embeddings (e.g. word2vec) as well as novel architectures (e.g. transformers).This success quickly invited researchers to explore the use of NLP techniques to other field, such as computer programming languages, with the promise to automate tasks in software programming (bug detection, code synthesis, code repair, cross language translation etc.). By extension, NLP has potential for application to network configuration languages as well, for instance considering tasks such as network configuration verification, synthesis, and cross-vendor translation. In this paper, we survey recent advances in deep learning applied to programming languages, for the purpose of code verification, synthesis and translation: in particularly, we review their training requirements and expected performance, and qualitatively assess whether similar techniques can benefit corresponding use-cases in networking.
• [SIGMETRICS-PEVA-22] Roberts, James and Rossi, Dario, "Size-Based Scheduling vs Fairness for Datacenter Flows: A Queuing Perspective" In ACM SIGMETRICS Perform. Eval. Rev., Vol. 50, No. 2, sep. 2022, arXiv Journal Abstract Bibtex

  @article{DR:SIGMETRICS-PEVA-22,
    author = {Roberts, James and Rossi, Dario},
    title = {Size-Based Scheduling vs Fairness for Datacenter Flows: A Queuing Perspective},
    year = {2022},
    month = sep,
    volume = {50},
    number = {2},
    url = {https://doi.org/10.1145/3561074.3561076},
    arxiv = {https://arxiv.org/abs/2203.12983},
    journal = {ACM SIGMETRICS Perform. Eval. Rev.},
    howpublished = {/ai4net/docs/rossi22sigmetrics-per.pdf},
    topic = {performance}
  }
  

  Contrary to the conclusions of a recent body of work where approximate shortest remaining processing time first (SRPT) flow scheduling is advocated for datacenter networks, this paper aims to demonstrate that imposing fairness remains a preferable objective. We evaluate abstract queuing models by analysis and simulation to illustrate the non-optimality of SRPT under the reasonable assumptions that datacenter source-destination flows occur in batches and bursts and not, as usually assumed, individually at the instants of a Poisson process. Results for these models have significant implications for the design of bandwidth sharing strategies for datacenter networks. In particular, we propose a novel "virtual fair scheduling" algorithm that enforces fairness between batches and is arguably simple enough to be implemented in high speed devices.
• [KDD-22] Huet, Alexis and Navarro, Jose Manuel and Rossi, Dario, "Local Evaluation of Time Series Anomaly Detection Algorithms" ACM SIGKDD Conference on Knowledge Discovery and Data mining (KDD) aug. 2022, arXiv Conference Abstract Bibtex

  @inproceedings{DR:KDD-22,
    title = {Local Evaluation of Time Series Anomaly Detection Algorithms},
    author = {Huet, Alexis and Navarro, Jose Manuel and Rossi, Dario},
    year = {2022},
    month = aug,
    booktitle = {ACM SIGKDD Conference on Knowledge Discovery and Data mining (KDD)},
    howpublished = {https://nonsns.github.io/paper/rossi22kdd.pdf},
    arxiv = {https://arxiv.org/abs/2206.13167},
    topic = {ad-algo}
  }
  

  In recent years, specific evaluation metrics for time series anomaly detection algorithms have been developed to handle the limitations of the classical precision and recall. However, such metrics are heuristically built as an aggregate of multiple desirable aspects, introduce parameters and wipe out the interpretability of the output. In this article, we first highlight the limitations of the classical precision/recall, as well as the main issues of the recent event-based metrics – for instance, we show that an adversary algorithm can reach high precision and recall on almost any dataset under weak assumption. To cope with the above problems, we propose a theoretically grounded, robust, parameter-free and interpretable extension to precision/recall metrics, based on the concept of “affiliation” between the ground truth and the prediction sets. Our metrics leverage measures of duration between ground truth and predictions, and have thus an intuitive interpretation. By further comparison against random sampling, we obtain a normalized precision/recall, quantifying how much a given set of results is better than a random baseline prediction. By construction, our approach keeps the evaluation local regarding ground truth events, enabling fine-grained visualization and interpretation of algorithmic results. We compare our proposal against various public time series anomaly detection datasets, algorithms and metrics. We further derive theoretical properties of the affiliation metrics that give explicit expectations about their behavior and ensure robustness against adversary strategies.
• [SIGCOMM-CCR-22] Wang, Chao and Finamore, Alessandro and Yang, Lixuan and Fauvel, Kevin and Rossi, Dario, "AppClassNet: A commercial-grade dataset for application identification research" In ACM SIGCOMM Computer Communication Review, Vol. 52, jul. 2022, DOI https://doi.org/10.1145/3561954.3561958 Journal Abstract Bibtex

  @article{DR:SIGCOMM-CCR-22,
    title = {{AppClassNet: A commercial-grade dataset for application identification research}},
    author = {Wang, Chao and Finamore, Alessandro and Yang, Lixuan and Fauvel, Kevin and Rossi, Dario},
    year = {2022},
    journal = {ACM SIGCOMM Computer Communication Review},
    month = jul,
    volume = {52},
    issue = {3},
    howpublished = {https://nonsns.github.io/paper/rossi22ccr.pdf},
    doi = {https://doi.org/10.1145/3561954.3561958},
    topic = {tc-train}
  }
  

  The recent success of Artificial Intelligence (AI) is rooted into several concomitant factors, namely theoretical progress coupled with abundance of data and computing power. Large companies can take advantage of a deluge of data, typically withhold from the research community due to privacy or business sensitivity concerns, and this is particularly true for networking data. Therefore, the lack of high quality data is often recognized as one of the main factors currently limiting networking research from fully leveraging AI methodologies potential. Following numerous requests we received from the scientific community, we release AppClassNet, a commercial-grade dataset for benchmarking traffic classification and management methodologies. AppClassNet is significantly larger than the datasets generally available to the academic community in terms of both the number of samples and classes, and reaches scales similar to the popular ImageNet dataset commonly used in computer vision literature. To avoid leaking user- and business-sensitive information, we opportunely anonymized the dataset, while empirically showing that it still represents a relevant benchmark for algorithmic research. In this paper, we describe the public dataset and our anonymization process. We hope that AppClassNet can be instrumental for other researchers to address more complex commercial-grade problems in the broad field of traffic classification and management.
• [ICML-22] Franzese, Giulio and Rossi, Simone and Yang, Lixuan and Finamore, Alessandro and Rossi, Dario and Filippone, Maurizio and Michiardi, Pietro, "How much diffusion time is enough?" ICML 2022 workshop on Continuous time methods for machine learning jun. 2022, Conference Abstract Bibtex

  @inproceedings{DR:ICML-22,
    author = {Franzese, Giulio and Rossi, Simone and Yang, Lixuan and Finamore, Alessandro and Rossi, Dario and Filippone, Maurizio and Michiardi, Pietro},
    title = {How much diffusion time is enough?},
    booktitle = {ICML 2022 workshop on Continuous time methods for machine learning},
    year = {2022},
    month = jun,
    howpublished = {https://nonsns.github.io/paper/rossi22icml.pdf},
    topic = {TBD}
  }
  

  Score-based diffusion models map noise into data using stochastic differential equations. While current practice advocates for a large T to ensure closeness to steady state, a smaller value of T should be preferred for a better approximation of the score-matching objective and computational efficiency. We conjecture, contrary to current belief and corroborated by numerical evidence, that the optimal diffusion times are smaller than current adoptions.
• [INFOCOM-22] Finamore, Alessandro and Roberts, James and Gallo, Massimo and Rossi, Dario, "Accelerating Deep Learning Classification with Error-controlled Approximate-key Caching" IEEE INFOCOM may. 2022, arXiv Conference Abstract Bibtex

  @inproceedings{DR:INFOCOM-22,
    title = {Accelerating Deep Learning Classification with Error-controlled Approximate-key Caching},
    author = {Finamore, Alessandro and Roberts, James and Gallo, Massimo and Rossi, Dario},
    booktitle = {IEEE INFOCOM},
    year = {2022},
    month = may,
    arxiv = {https://arxiv.org/abs/2112.06671},
    howpublished = {https://nonsns.github.io/paper/rossi22infocom.pdf},
    topic = {tc-system}
  }
  

  While Deep Learning (DL) technologies are a promising tool to solve networking problems that map to classification tasks, their computational complexity is still too high with respect to real-time traffic measurements requirements. To reduce the DL inference cost, we propose a novel caching paradigm, that we named approximate-key caching, which returns approximate results for lookups of selected input based on cached DL inference results. While approximate cache hits alleviate DL inference workload and increase the system throughput, they however introduce an approximation error. As such, we couple approximate-key caching with an error-correction principled algorithm, that we named auto-refresh. We analytically model our caching system performance for classic LRU and ideal caches, we perform a trace-driven evaluation of the expected performance, and we compare the benefits of our proposed approach with the state-of-the-art similarity caching – testifying the practical interest of our proposal.
• [AAAI-22] Boffa, Matteo and Houidi, Zied Ben and Krolikowski, Jonatan and Rossi, Dario, "Neural combinatorial optimization beyond the TSP: Existing architectures under-represent graph structure" AAAI workshop on Graphs and more complex structures for learning and reasoning (GLCR’22) 2022, arXiv Conference Abstract Bibtex

  @inproceedings{DR:AAAI-22,
    title = {Neural combinatorial optimization beyond the TSP: Existing architectures under-represent graph structure},
    author = {Boffa, Matteo and Houidi, Zied Ben and Krolikowski, Jonatan and Rossi, Dario},
    year = {2022},
    booktitle = {AAAI workshop on Graphs and more complex structures for learning and reasoning (GLCR'22)},
    howpublished = {https://nonsns.github.io/paper/rossi22aaai-glcr.pdf},
    arxiv = {https://arxiv.org/abs/2201.00668},
    topic = {wlan}
  }
  

  Recent years have witnessed the promise that reinforcement learning, coupled with Graph Neural Network (GNN) architectures, could learn to solve hard combinatorial optimization problems: given raw input data and an evaluator to guide the process, the idea is to automatically learn a policy able to return feasible and high-quality outputs. Recent work have shown promising results but the latter were mainly evaluated on the travelling salesman problem (TSP) and similar abstract variants such as Split Delivery Vehicle Routing Problem (SDVRP). This paper assesses how and whether recent neural architectures also transfer to graph problems of practical interest. We thus set out to systematically transfer these architectures to the Power and Channel Allocation Problem (PCAP), which has practical relevance for, e.g., radio resource allocation in wireless networks. Our experimental results suggest that existing architectures (i) are still incapable of capturing graph structural features and (ii) are not suitable for problems where the actions on the graph change the graph attributes. On a positive note, we show that augmenting the structural representation of problems with Distance Encoding is a promising step towards the still-ambitious goal of learning multi-purpose autonomous solvers.
• [CoNEXT-21a] Gioacchini, Luca and Vassio, Luca and Mellia, Marco and Drago, Idilio and Ben Houidi, Zied and Rossi, Dario, "DarkVec: Automatic Analysis of Darknet Traffic with Word Embeddings" ACM CoNEXT, Runner-up for best paper award dec. 2021, Conference Runner-up Abstract Bibtex

  @inproceedings{DR:CoNEXT-21a,
    author = {Gioacchini, Luca and Vassio, Luca and Mellia, Marco and Drago, Idilio and Ben Houidi, Zied and Rossi, Dario},
    title = {DarkVec: Automatic Analysis of Darknet Traffic with Word Embeddings},
    booktitle = {ACM CoNEXT, Runner-up for best paper award},
    year = {2021},
    note = {bestpaperrunnerup},
    month = dec,
    partner = {polito-mellia},
    howpublished = {https://nonsns.github.io/paper/rossi21conext-a.pdf},
    topic = {network-security}
  }
  

  Darknets are passive probes listening to traffic reaching IP addresses that host no services. Traffic reaching them is unsolicited by nature and often induced by scanners, malicious senders and misconfigured hosts. Its peculiar nature makes it a valuable source of information to learn about malicious activities. However, the massive amount of packets and sources that reach darknets makes it hard to extract meaningful insights. In particular, multiple senders contact the darknet while performing similar and coordinated tasks, which are often commanded by common controllers (botnets, crawlers, etc.). How to automatically identify and group those senders that share similar behaviors remains an open problem. We here introduce DarkVec, a methodology to identify clusters of senders (i.e., IP addresses) engaged in similar activities on darknets. DarkVec leverages word embedding techniques (e.g., Word2Vec) to capture the co-occurrence patterns of sources hitting the darknets. We extensively test DarkVec and explore its design space in a case study using one month of darknet data. We show that with a proper definition of service, the generated embeddings can be easily used to (i) associate unknown senders’ IP addresses to the correct known labels (more than 96% accuracy), and (ii) identify new attack and scan groups of previously unknown senders. We contribute DarkVec source code and datasets to the community also to stimulate the use of word embeddings to automatically learn patterns on generic traffic traces
• [CoNEXT-21b] Azorin, Raphael and Gallo, Massimo and Finamore, Alessandro and Filippone, Maurizio and Michiardi, Pietro and Rossi, Dario, "Towards a Generic Deep Learning Pipeline for Traffic Measurements" ACM CoNEXT, Student Workshop dec. 2021, Conference Bibtex

  @inproceedings{DR:CoNEXT-21b,
    author = {Azorin, Raphael and Gallo, Massimo and Finamore, Alessandro and Filippone, Maurizio and Michiardi, Pietro and Rossi, Dario},
    title = {Towards a Generic Deep Learning Pipeline for Traffic Measurements},
    booktitle = {ACM CoNEXT, Student Workshop},
    year = {2021},
    month = dec,
    howpublished = {https://nonsns.github.io/paper/rossi21conext-b.pdf},
    topic = {measurement}
  }
  
• [SEC-21] Gallo, Massimo and Finamore, Alessandro and Simon, Gwendal and Rossi, Dario, "FENXI: Fast In-Network Analytics" IEEE/ACM Symposium on Edge Computing (SEC) dec. 2021, arXiv Conference Abstract Bibtex

  @inproceedings{DR:SEC-21,
    author = {Gallo, Massimo and Finamore, Alessandro and Simon, Gwendal and Rossi, Dario},
    title = {{FENXI}: Fast In-Network Analytics},
    booktitle = {IEEE/ACM Symposium on Edge Computing (SEC)},
    year = {2021},
    month = dec,
    howpublished = {https://nonsns.github.io/paper/rossi21sec.pdf},
    arxiv = {http://arxiv.org/abs/2105.11738},
    topic = {tc-system}
  }
  

  Live traffic analysis at the first aggregation point in the ISP network enables the implementation of complex traffic engineering policies but is limited by the scarce processing capabilities, especially for Deep Learning (DL) based analytics. The introduction of specialized hardware accelerators i.e., Tensor Processing Unit (TPU), offers the opportunity to enhance processing capabilities of network devices at the edge. Yet, to date, no packet processing pipeline is capable of offering DL-based analysis capabilities in the data-plane, without interfering with network operations. In this paper, we present FENXI, a system to run complex analytics by leveraging TPU. The design of FENXI decouples forwarding operations and traffic analytics which operates at different granularities i.e., packet and flow levels. We conceive two independent modules that asynchronously communicate to exchange network data and analytics results, and design data structures to extract flow level statistics without impacting per-packet processing. We prototype FENXI on a general-purpose server and evaluate its performance in both adversarial and realistic network conditions. Our evaluation shows that FENXI is able to offer DL processing to 100 Gbps linecards with a limited number of resources, while also dynamically adapting to network conditions.
• [TNSM-21b] Yang, Lixuan and Finamore, Alessandro and Feng, Jun and Rossi, Dario, "Deep Learning and Zero-Day Traffic Classification: Lessons learned from a commercial-grade dataset" In IEEE Transactions on Network and Service Management, Vol. 18, No. 4, pp.4103–4118, dec. 2021, DOI 10.1109/TNSM.2021.3122940 arXiv Journal Abstract Bibtex

  @article{DR:TNSM-21b,
    author = {{Yang}, Lixuan and {Finamore}, Alessandro and {Feng}, Jun and {Rossi}, Dario},
    title = {Deep Learning and Zero-Day Traffic Classification: Lessons learned from a commercial-grade dataset},
    journal = {IEEE Transactions on Network and Service Management},
    volume = {18},
    number = {4},
    pages = {4103--4118},
    year = {2021},
    month = dec,
    doi = {10.1109/TNSM.2021.3122940},
    arxiv = {https://arxiv.org/abs/2104.03182},
    howpublished = {https://nonsns.github.io/paper/rossi21tnsm-b.pdf},
    topic = {tc-algo}
  }
  

  The increasing success of Machine Learning (ML) and Deep Learning (DL) has recently re-sparked interest towards traffic classification. While supervised techniques provide satisfactory performance when classifying known traffic, the detection of zero-day (i.e., unknown) traffic is a more challenging task. At the same time, zero-day detection, generally tackled with unsupervised techniques such as clustering, received less coverage by the traffic classification literature which focuses more on deriving DL models via supervised techniques. Moreover, the combination of supervised and unsupervised techniques poses challenges not fully covered by the traffic classification literature. In this paper, we share our experience on a commercial-grade DL traffic classification engine that combines supervised and unsupervised techniques to identify known and zero-day traffic. In particular, we rely on a dataset with hundreds of very fine grained application labels, and perform a thorough assessment of two state of the art traffic classifiers in commercial-grade settings. This pushes the boundaries of traffic classifiers evaluation beyond the few tens of classes typically used in the literature. Our main contribution is the design and evaluation of GradBP, a novel technique for zero-day applications detection. Based on gradient backpropagation and tailored for DL models, GradBP yields superior performance with respect to state of the art alternatives, in both accuracy and computational cost. Overall, while ML and DL models are both equally able to provide excellent performance for the classification of known traffic, the non-linear feature extraction process of DL models backbone provides sizable advantages for the detection of unknown classes over classical ML models
• [NETMAG-21] Yang, Lixuan and and Dario Rossi, "Quality monitoring and assessment of deployed Deep Learning models for Network AIOps" In IEEE Network Magazine,, pp.84-90, nov. 2021, DOI 10.1109/MNET.001.2100227 Journal Abstract Bibtex

  @article{DR:NETMAG-21,
    author = {{Yang}, Lixuan and and Dario {Rossi}},
    title = {Quality monitoring and assessment of deployed Deep Learning models for Network AIOps},
    journal = {IEEE Network Magazine,},
    year = {2021},
    month = nov,
    vol = {35},
    issue = {6},
    pages = {84-90},
    doi = {10.1109/MNET.001.2100227},
    topic = {tc-algo},
    howpublished = {https://nonsns.github.io/paper/rossi21netmag.pdf}
  }
  

  Artificial Intelligence (AI) has recently attracted a lot of attention, transitioning from research labs to a wide range of successful deployments in many fields, which is particularly true for Deep Learning (DL) techniques. Ultimately, DL models are software artifacts, that, as any software realization, need to be regularly maintained and updated: consequently, as a logical extension of the DevOps software development practices to AI-software applied to network operation and management, AIOps foresee to continuously push evolved models in production networks. While for some network use-cases DL models can be incrementally updated at relatively low cost, the more typical case is that updating deployed DL models has a significant cost that needs to be managed. It follows that, during the lifecycle of DL model deployment, it is important to assess the relative “staleness” of deployed DL models, so to prioritize update of “ageing” models. In this article, we cover the issue of quality assessment and tracking of DL models deployed for network management purposes.
• [TMA-21] Bovenzi, Giampaolo and Yang, Lixuan and Finamore, Alessandro and Aceto, Giuseppe and Ciuonzo, Domenico and Pescape, Antonio and Rossi, Dario, "A First Look at Class Incremental Learning in Deep Learning Mobile Traffic" IFIP Traffic Monitoring and Analysis (TMA) sep. 2021, Conference Abstract Bibtex

  @inproceedings{DR:TMA-21,
    author = {Bovenzi, Giampaolo and Yang, Lixuan and Finamore, Alessandro and Aceto, Giuseppe and Ciuonzo, Domenico and Pescape, Antonio and Rossi, Dario},
    title = {A First Look at Class Incremental Learning in Deep Learning Mobile Traffic},
    booktitle = {IFIP Traffic Monitoring and Analysis (TMA)},
    year = {2021},
    month = sep,
    howpublished = {https://nonsns.github.io/paper/rossi21tma.pdf},
    topic = {tc-train}
  }
  

  The recent popularity growth of Deep Learning (DL) re-ignited the interest towards traffic classification, with several studies demonstrating the accuracy of DL-based classifiers to identify Internet applications’ traffic. Even with the aid of hardware accelerators (GPUs, TPUs), DL model training remains expensive, and limits the ability to operate frequent model updates necessary to fit to the ever evolving nature of Internet traffic, and mobile traffic in particular. To address this pain point, in this work we explore Incremental Learning (IL) techniques to add new classes to models without a full retraining, hence speeding up model’s updates cycle. We consider iCarl, a state of the art IL method, and MIRAGE-2019, a public dataset with traffic from 40 Android apps, aiming to understand if there is a case for incremental learning in traffic classification. By dissecting iCarl internals, we discuss ways to improve its design, contributing a revised version, namely iCarl+. Despite our analysis reveals their infancy, IL techniques are a promising research area on the roadmap towards automated DL-based traffic analysis systems.
• [NETWORKING-21] Iacoboaiea, Ovidiu and Krolikowski, Jonatan and Ben Houidi, Zied and Rossi, Dario, "Real-Time Channel Management in WLANs: Deep Reinforcement Learning Versus Heuristics" IFIP Networking jun. 2021, Conference Abstract Bibtex

  @inproceedings{DR:NETWORKING-21,
    author = {Iacoboaiea, Ovidiu and Krolikowski, Jonatan and {Ben Houidi}, Zied and Rossi, Dario},
    title = {{Real-Time} Channel Management in {WLANs:} Deep Reinforcement Learning Versus Heuristics},
    booktitle = {IFIP Networking},
    address = {Helsinki, Finland},
    month = jun,
    year = {2021},
    howpublished = {https://nonsns.github.io/paper/rossi21networking.pdf},
    topic = {wlan}
  }
  

  Today’s WLANs rely on a centralized Access Controller (AC) entity for managing distributed wireless Access Points (APs) to which user devices connect. The availability of real-time analytics at the AC opens the possibility to automate the allocation of scarce radio resources, continuously adapting to changes in traffic demands. Often, the allocation problem is formulated in terms of weighted graph coloring, which is NP-hard, and custom heuristics are used to find satisfactory solutions. In this paper, we contrast solutions that are based on (and even improve) state of the art heuristics to a data-driven solution that leverages Deep Reinforcement Learning (DRL). Based on both simulation results as well as experiments in a real deployment, we show that our DRL-based scheme not only learns to solve the complex combinatorial problem in bounded time, outperforming heuristics, but it also exhibits appealing generalization properties, e.g. to different network sizes and densities.
• [ICML-UDL-21] Yang, Lixuan and Rossi, Dario, "Thinkback: Task Specific Out-of-Distribution Detection" International Conference on Machine Learning (ICML) workshop on Uncertainty and Robustness in Deep Learning (UDL) 2021 jun. 2021, Conference Abstract Bibtex

  @inproceedings{DR:ICML-UDL-21,
    author = {{Yang}, Lixuan and {Rossi}, Dario},
    title = {Thinkback: Task Specific Out-of-Distribution Detection},
    year = {2021},
    month = jun,
    booktitle = {International Conference on Machine Learning (ICML) workshop on Uncertainty and Robustness in Deep Learning (UDL) 2021},
    topic = {tc-algo},
    howpublished = {https://nonsns.github.io/paper/rossi21icml-udl.pdf}
  }
  

  The increased success of Deep Learning (DL) has recently sparked large-scale deployment of DL models in many diverse industry segments. Yet, a crucial weakness of supervised model is the inherent difficulty in handling out-of-distribution samples, i.e., samples belonging to classes that were not presented to the model at training time. We propose in this paper a novel way to formulate the out-of-distribution detection problem, tailored for DL models. Our method does not require fine tuning process on training data, yet is significantly more accurate than the state of the art for out-ofdistribution detection.
• [INFOCOM-21] Krolikowski, Jonatan and Iacoboaiea, Ovidiu and Houidi, Zied Ben and Rossi, Dario, "WiFi Dynoscope: Interpretable Real-Time WLAN Optimization" IEEE INFOCOM, Demo session may. 2021, DOI Conference Abstract Bibtex

  @inproceedings{DR:INFOCOM-21,
    author = {Krolikowski, Jonatan and Iacoboaiea, Ovidiu and Houidi, Zied Ben and Rossi, Dario},
    title = {WiFi Dynoscope: Interpretable Real-Time WLAN Optimization},
    booktitle = {IEEE INFOCOM, Demo session},
    month = may,
    year = {2021},
    volume = {},
    pages = {},
    doi = {},
    howpublished = {https://nonsns.github.io/paper/rossi21infocom.pdf},
    topic = {wlan}
  }
  

  Today’s Wireless Local Area Networks (WLANs) rely on a centralized Access Controller (AC) entity for managing a fleet of Access Points (APs). Real-time analytics enable the AC to optimize the radio resource allocation (i.e. channels) on-line in response to sudden traffic shifts. Deep Reinforcement Learning (DRL) relieves the pressure of finding good optimization heuristics by learning a policy through interactions with the environment. However, it is not granted that DRL will behave well in unseen conditions. Tools such as the WiFi Dynoscope introduced here are necessary to gain this trust. In a nutshell, this demo dissects the dynamics of WLAN networks, both simulated and from real large-scale deployments, by (i) comparatively analyzing the performance of different algorithms on the same deployment at high level and (ii) getting low-level details and insights into algorithmic behaviour.
• [TECHREP-21-DRL] Iacoboaiea, Ovidiu and Krolikowski, Jonatan and Houidi, Zied Ben and Rossi, Dario, "The long and winding road to Deep Autonomous Networks: Lessons from real WLAN deployment" apr. 2021, Tech.Rep. Abstract Bibtex

  @techreport{DR:TECHREP-21-DRL,
    author = {Iacoboaiea, Ovidiu and Krolikowski, Jonatan and Houidi, Zied Ben and Rossi, Dario},
    title = {The long and winding road to Deep Autonomous Networks: Lessons from real WLAN deployment},
    year = {2021},
    month = apr,
    topic = {wlan-algo},
    howpublished = {https://nonsns.github.io/paper/rossi21techrep_DRL_deploy.pdf}
  }
  

  Deep Reinforcement Learning (DRL) techniques have recently gathered much attention for their ability to learn taking complex decisions in different fields: as such, they are an appealing candidate for network Operation and Management (O&M). In particular, DRL can become a fundamental item in the toolbox of the so called “self-driving networks”, especially for tasks such as dynamic resource allocation, that is generally formulated and solved as complex optimization problems. Yet, training and deployment of DRL agents in real-world scenarios face important challenges, that we illustrate in this article using Wireless LANs as a relevant deployment example.
• [TNSM-21a] Huet, Alexis and Saverimoutou, Antoine and Houidi, Zied Ben and Shi, Hao and Cai, Shengming and Xu, Jinchun and Mathieu, Bertrand and Rossi, Dario, "Deployable models for approximating web QoE metrics from encrypted traffic" In IEEE Transactions on Network and Service Management, pp.839-854, mar. 2021, DOI 10.1109/TNSM.2020.3037019 Journal Abstract Bibtex

  @article{DR:TNSM-21a,
    title = {Deployable models for approximating web QoE metrics from encrypted traffic},
    author = {Huet, Alexis and Saverimoutou, Antoine and Houidi, Zied Ben and Shi, Hao and Cai, Shengming and Xu, Jinchun and Mathieu, Bertrand and Rossi, Dario},
    journal = {IEEE Transactions on Network and Service Management},
    year = {2021},
    month = mar,
    vol = {18},
    issue = {1},
    pages = {839-854},
    doi = {10.1109/TNSM.2020.3037019},
    howpublished = {https://nonsns.github.io/paper/rossi21tnsm-a.pdf},
    topic = {qoe-web}
  }
  

  Being on endpoints, Content Providers can easily evaluate end users’ web browsing quality of experience (web QoE) by accessing in-browser computed application-level metrics. Because of end-to-end traffic encryption, it is becoming considerably harder for Internet Service Providers (ISPs) to evaluate the web QoE of their customers, which is important for management purposes. In this paper, we propose data-driven machine learning techniques and exact flow-level algorithmic methods to infer well-known application-level web performance metrics (such as SpeedIndex and Page Load Time) from raw encrypted streams of network traffic. We prove the efficiency of our approach taking as input a unique dataset of more than 200,000 experiments, targeting a large set of popular pages (Alexa top-500), from probes from several ISPs networks, with different browsers (Chrome, Firefox) and viewport combinations. Results show that our data-driven models are not only accurate for several web performance metrics, but also feature the ability to generalize to previously unseen conditions. Furthermore, we discuss how our extremely lightweight flow-level method has a provable accuracy on a specific metric, and is thus of particular appeal from a deployment viewpoint
• [CNSM-20b] Huet, Alexis and Houidi, Zied Ben and Mathieu, Bertrand and Rossi, Dario, "Detecting Degradation of Web Browsing Quality of Experience (QoE)" IEEE International Conference on Network and Service Management (CNSM) nov. 2020, DOI Conference Abstract Bibtex

  @inproceedings{DR:CNSM-20b,
    author = {Huet, Alexis and Houidi, Zied Ben and Mathieu, Bertrand and Rossi, Dario},
    title = {Detecting Degradation of Web Browsing Quality of Experience (QoE)},
    booktitle = {IEEE International Conference on Network and Service Management (CNSM)},
    month = nov,
    year = {2020},
    volume = {},
    pages = {},
    doi = {},
    howpublished = {https://nonsns.github.io/paper/rossi20cnsm-b.pdf},
    topic = {web-qoe}
  }
  

  Quality of Experience (QoE) inference, and particularly the detection of its degradation is an important management tool for ISPs. Yet, this task is made difficult due to widespread use of encryption on the data-plane on the one hand so that measuring QoE is hard, and to the ephemeral properties of the web content on the other hand so that changes in QoE indicators may be rooted in changes in properties of the content itself, more than being caused by network-related events. In this paper, we phrase the QoE degradation detection issue as a change point detection problem, that we tackle by leveraging a unique dataset consisting on several hundreds thousands browsing sessions spanning multiple months. Our results, beyond showing feasibility, warn about the exclusive use of QoE indicators that are very close to content, as changes in the content space can lead to false alarms that are not tied to network-related problems.
• [ICDM-20] Putina, Andrian and Sozio, Mauro and Navarro, Jose M. and Rossi, Dario, "Random Histogram Forest for Unsupervised Anomaly Detection" 20th IEEE International Conference on Data Mining (ICDM) nov. 2020, DOI Conference Abstract Bibtex

  @inproceedings{DR:ICDM-20,
    author = {Putina, Andrian and Sozio, Mauro and Navarro, Jose M. and Rossi, Dario},
    title = {Random Histogram Forest for Unsupervised Anomaly Detection},
    booktitle = {20th IEEE International Conference on Data Mining (ICDM)},
    month = nov,
    year = {2020},
    volume = {},
    pages = {},
    doi = {},
    howpublished = {https://nonsns.github.io/paper/rossi20icdm.pdf},
    topic = {ad-algo}
  }
  

  Roughly speaking, anomaly detection consists of identifying instances whose features significantly deviate from the rest of input data. It is one of the most widely studied problems in unsupervised machine learning, boasting applications in network intrusion detection, fraud detection, healthcare and many others. Several methods have been developed in recent years, however, a satisfactory solution is still missing to the best of our knowledge. We present Random Histogram Forest an effective approach for unsupervised anomaly detection. Our approach is probabilistic, which has been proved to be effective in identifying anomalies. Moreover, it employs the fourth central moment (aka kurtosis), so as to identify potential anomalous instances. We conduct an extensive experimental evaluation on 38 datasets including all benchmarks for anomaly detection, as well as the most successful algorithms for unsupervised anomaly detection, to the best of our knowledge. Moreover, we provide some novel datasets that are made publicly available. We evaluate all the approaches in terms of the average precision of the area under the precision-recall curve (AP) as well as ROC. Our evaluation shows that our approach significantly outperforms all other approaches, both in terms of both AP and ROC, while boasting linear running time.
• [CNSM-20a] Wassermann, Sarah and Casas, Pedro and Houidi, Zied Ben and Huet, Alexis and Seufert, Michael and Wehner, Nikolas and Schuler, Joshua and Cai, Sheng-Ming and Shi, Hao and Xu, Jinchun and Hossfeld, Tobias and Rossi, Dario, "Are you on Mobile or Desktop? On the Impact of End-User Device on Web QoE Inference from Encrypted Traffic" IEEE International Conference on Network and Service Management (CNSM) nov. 2020, DOI Conference Abstract Bibtex

  @inproceedings{DR:CNSM-20a,
    author = {Wassermann, Sarah and Casas, Pedro and Houidi, Zied Ben and Huet, Alexis and Seufert, Michael and Wehner, Nikolas and Schuler, Joshua and Cai, Sheng-Ming and Shi, Hao and Xu, Jinchun and Hossfeld, Tobias and Rossi, Dario},
    title = {Are you on Mobile or Desktop? On the Impact of End-User Device on Web QoE Inference from Encrypted Traffic},
    booktitle = {IEEE International Conference on Network and Service Management (CNSM)},
    month = nov,
    year = {2020},
    volume = {},
    pages = {},
    doi = {},
    howpublished = {https://nonsns.github.io/paper/rossi20cnsm-a.pdf},
    topic = {web-qoe}
  }
  

  Web browsing is one of the key applications of the Internet, if not the most important one. We address the problem of Web Quality-of-Experience (QoE) monitoring from the ISP perspective, relying on in-network, passive measurements. As a proxy to Web QoE, we focus on the analysis of the well-known SpeedIndex (SI) metric. Given the lack of application-level-data visibility introduced by the wide adoption of end-to-end encryption, we resort to machine-learning models to infer the SI and the QoE level of individual web-page loading sessions, using as input only packet- and flow-level data. In this paper, we study the impact of different end-user device types (e.g., smartphone, desktop, tablet) on the performance of such models. Empirical evaluations on a large, multi-device, heterogeneous corpus of Web-QoE measurements for the most popular websites demonstrate that the proposed solution can infer the SI as well as estimate QoE ranges with high accuracy, using either packet-level or flow-level measurements. In addition, we show that the device type adds a strong bias to the feasibility of these Web-QoE models, putting into question the applicability of previously conceived approaches on single-device measurements. To improve the state of the art, we conceive cross-device generalizable models operating at both packet and flow levels, offering a feasible solution for Web-QoE monitoring in operational, multi-device networks. To the best of our knowledge, this is the first study tackling the analysis of Web QoE from encrypted network traffic in multi-device scenarios.
• [TNSM-20b] Putina, Andrian and Rossi, Dario, "Online anomaly detection leveraging stream-based clustering and real-time telemetry" In IEEE Transactions on Network and Service Management, Vol. 18, No. 1, pp.–, nov. 2020, DOI 110.1109/TNSM.2020.3037019 Journal Abstract Bibtex

  @article{DR:TNSM-20b,
    author = {Putina, Andrian and Rossi, Dario},
    journal = {IEEE Transactions on Network and Service Management},
    title = {Online anomaly detection leveraging stream-based clustering and real-time telemetry},
    year = {2020},
    month = nov,
    volume = {18},
    number = {1},
    pages = {--},
    doi = {110.1109/TNSM.2020.3037019},
    howpublished = {https://nonsns.github.io/paper/rossi20tnsm-b.pdf},
    topic = {ad-algo}
  }
  

  Recent technology evolution allows network equipment to continuously stream a wealth of “telemetry” information, which pertains to multiple protocols and layers of the stack, at a very fine spatial-grain and high-frequency. This deluge of telemetry data clearly offers new opportunities for network control and troubleshooting, but also poses a serious challenge for what concerns its real-time processing. We tackle this challenge by applying streaming machine-learning techniques to the continuous flow of control and data-plane telemetry data, with the purpose of real-time detection of anomalies. In particular, we implement an anomaly detection engine that leverages DenStream, an unsupervised clustering technique, and apply it to features collected from a large-scale testbed comprising tens of routers traversed up to 3 Terabit/s worth of real application traffic. We contrast DenStream with offline algorithms such as DBScan and Local Outlier Factor (LOF), as well as online algorithms such as the windowed version of DBScan, ExactSTORM, Continuous Outlier Detection (COD) and Robust Random Cut Forest (RRCF). Our experimental campaign compares these seven algorithms under both accuracy and computational complexity viewpoints: results testify that DenStream (i) achieves detection results on par with RRCF, the best performing algorithm and (ii) is significantly faster than other approaches, notably over two orders of magnitude faster than RRCF. In spirit with the recent trend toward reproducibility of results, we make our code available as open source to the scientific community.
• [IJCAIFL-20] Yang, Lixuan and Beliard, Cedric and Rossi, Dario, "Heterogeneous Data-Aware Federated Learning" International Joint Conference on Artificial Intelligence (IJCAI), Workshop on Federated Learning sep. 2020, DOI Conference Abstract Bibtex

  @inproceedings{DR:IJCAIFL-20,
    author = {Yang, Lixuan and Beliard, Cedric and Rossi, Dario},
    title = {Heterogeneous Data-Aware Federated Learning},
    booktitle = {International Joint Conference on Artificial Intelligence (IJCAI), Workshop on Federated Learning},
    month = sep,
    year = {2020},
    volume = {},
    pages = {},
    doi = {},
    howpublished = {https://nonsns.github.io/paper/rossi20ijcai-fl.pdf},
    topic = {tc-train}
  }
  

  Federated learning (FL) is an appealing concept to perform distributed training of Neural Networks (NN) while keeping data private. With the industrialization of the FL framework, we identify several problems hampering its successful deployment, such as presence of non i.i.d data, disjoint classes, signal multi-modality across datasets. In this work, we address these problems by proposing a novel method that not only (1) aggregates generic model parameters (e.g. a common set of task generic NN layers) on server (e.g. in traditional FL), but also (2) keeps a set of parameters (e.g, a set of task specific NN layer) specific to each client. We validate our method on the traditionally used public benchmarks (e.g., Femnist) as well as on our proprietary collected dataset (i.e., traffic classification). Results show the benefit of our method, with significant advantage on extreme cases.
• [IJCAI-NETAML-20] Yang, Lixuan and Finamore, Alessandro and Rossi, Dario, "Deep Learning and Traffic Classification: A critical review with novel" International Joint Conference on Artificial Intelligence (IJCAI), Workshop on Network Traffic Analytics using Machine Learning sep. 2020, Conference Abstract Bibtex

  @inproceedings{DR:IJCAI-NETAML-20,
    author = {Yang, Lixuan and Finamore, Alessandro and Rossi, Dario},
    title = {Deep Learning and Traffic Classification: A critical review with novel},
    booktitle = {International Joint Conference on Artificial Intelligence (IJCAI), Workshop on Network Traffic Analytics using Machine Learning},
    howpublished = {https://nonsns.github.io/paper/rossi20ijcai-netaml.pdf},
    month = sep,
    year = {2020}
  }
  

  The increased success of Convolutional Neural Networks (CNNs) has recently re-sparked interest towards traffic classification (TC). New literature shows the potential of reaching perfect classification accuracy, yet at the core of those works still reside the same limitations surfaced in the 1st wave of TC techniques, started in early 2000s and culminated with the application of Machine Learning (ML) for "early classification". To better highlight and discuss such issues, in this paper we report on novel insights based on a commercial-grade traffic classification engine. We aim to perform a critical review of the state of the art, introducing the research community to problems arising at a commercial scale (30× the largest number of classes in academic literature), discussing the pitfalls and how to avoid them. Leveraging a dataset comprising millions of flows and thousands of labels, we perform a fair comparison of classic Machine Learning (ML) and novel Deep Learning (DL) architectures based on the same inputs. We additionally put emphasis that comparing techniques on the mere raw performance make no sense unless they are fairly compared in terms of their computational requirements, an often forgotten key aspect affecting deployment.
• [ITC-20] Navarro, Jose M. and Rossi, Dario, "HURRA! Human readable router anomaly detection" sep. 2020, DOI Award Abstract Bibtex

  @inproceeding{DR:ITC-20,
    author = {Navarro, Jose M. and Rossi, Dario},
    title = {HURRA! Human readable router anomaly detection},
    booktitle = {International Teletraffic Congress (ITC32)},
    month = sep,
    year = {2020},
    volume = {},
    pages = {},
    doi = {},
    note = {bestpaperaward},
    howpublished = {https://nonsns.github.io/paper/rossi20itc.pdf},
    topic = {ad-fs}
  }
  

  This paper presents HURRA, a system that aims to reduce the time spent by human operators in the process of network troubleshooting. To do so, it comprises two modules that are plugged after any anomaly detection algorithm: (i) a first attention mechanism, that ranks the present features in terms of their relation with the anomaly and (ii) a second module able to incorporates previous expert knowledge seamlessly, without any need of human interaction nor decisions. We show the efficacy of these simple processes on a collection of real router datasets obtained from tens of ISPs which exhibit a rich variety of anomalies and very heterogeneous set of KPIs, on which we gather manually annotated ground truth by the operator solving the troubleshooting ticket. Our experimental evaluation shows that (i) the proposed system is effective in achieving high levels of agreement with the expert, that (ii) even a simple statistical approach is able to extracting useful information from expert knowledge gained in past cases to further improve performance and finally that (iii) the main difficulty in live deployment concerns the automated selection of the anomaly detection algorithm and the tuning of its hyper-parameters.
• [SIGCOMM-20] Gallo, Massimo and Finamore, Alessandro and Simon, Gwendal and Rossi, Dario, "Real-time Deep Learning based Traffic Analytics" ACM SIGCOMM, Demo session aug. 2020, DOI Conference Abstract Bibtex

  @inproceedings{DR:SIGCOMM-20,
    author = {Gallo, Massimo and Finamore, Alessandro and Simon, Gwendal and Rossi, Dario},
    title = {Real-time Deep Learning based Traffic Analytics},
    booktitle = {ACM SIGCOMM, Demo session},
    month = aug,
    year = {2020},
    volume = {},
    pages = {},
    doi = {},
    howpublished = {https://nonsns.github.io/paper/rossi20sigcomm.pdf},
    topic = {tc-system}
  }
  

  The increased interest towards Deep Learning (DL) tech-nologies has led to the development of a new generation of specialized hardware accelerator such as Graphic Processing Unit (GPU) and Tensor Processing Unit (TPU). The integration of such components in network routers is however not trivial. Indeed, routers typically aim to minimize the overhead of per-packet processing, and design choices to integrate a new accelerator need to factor in these key requirements. The literature and benchmarks on DL hardware accelerators have overlooked specific router constraints (e.g., strict latency) and focused instead on cloud deployment and image processing. Likewise,there is limited literature regarding DL application on traffic processing at line-rate. Among all hardware accelerators, we are interested in edge TPUs. Since their design focuses on DL inference, edge TPUs matches the vision of operators, who consider running pre-trained DL models in routers with low power drain. Edge TPUs are expected to limit the amount of computational resources for inference and to yield a higher ratio of operations-per-watt footprint than GPUs.This demo aims to investigate the operational points at which edge TPUs become a viable option, using traffic classification as a use case. We sketch the design of a real-time DL traffic classification system, and compare inference speed (i.e., number of classifications per second) of a state-of-the-art Convolutional Neural Network (CNN) model running on different hardware (CPU, GPU, TPU). To constrast their performance, we run stress tests based on synthetic traffic and under different conditions. We collect the results into a dashboard which enables network operators and system designers to both explore the stress test results with regards to their considered operational points, as well as triggering synthetic live tests on top of Ascend310 TPUs.
• [INFOCOM-20c] Sviridov, German and Beliard, Cedric and Simon, Gwendal and Bianco, Andrea and Giaccone, Paolo and Rossi, Dario, "Leveraging AI players for QoE estimation in cloud gaming" IEEE INFOCOM, Demo session jul. 2020, DOI Conference Abstract Bibtex

  @inproceedings{DR:INFOCOM-20c,
    author = {Sviridov, German and Beliard, Cedric and Simon, Gwendal and Bianco, Andrea and Giaccone, Paolo and Rossi, Dario},
    title = {Leveraging AI players for QoE estimation in cloud gaming},
    booktitle = {IEEE INFOCOM, Demo session},
    month = jul,
    year = {2020},
    volume = {},
    pages = {},
    doi = {},
    howpublished = {https://nonsns.github.io/paper/rossi20infocom-c.pdf},
    topic = {game-qoe}
  }
  

  Quality of Experience (QoE) assessment in video games is notorious for its burdensomeness. Employing human subjects to understand network impact on the perceived gaming QoE presents major drawbacks in terms of resources requirement, results interpretability and poor transferability across different games. To overcome these shortcomings, we propose to substitute human players with artificial agents trained with state-of-the-art Deep Reinforcement Learning techniques. Equivalently to traditional QoE assessment, we measure the in-game score achieved by an artificial agent for the game of Doom for varying network parameters. Our results show that the proposed methodology can be applied to understand fine-grained impact of network conditions on gaming experience while opening a lot of new opportunities for network operators and game developers.
• [INFOCOM-20b] Beliard, Cedric and Finamore, Alessandro and Rossi, Dario, "Opening the Deep Pandora Box: Explainable Traffic Classification" IEEE INFOCOM, Demo session jul. 2020, DOI Conference Abstract Bibtex

  @inproceedings{DR:INFOCOM-20b,
    author = {Beliard, Cedric and Finamore, Alessandro and Rossi, Dario},
    title = {Opening the Deep Pandora Box: Explainable Traffic Classification},
    booktitle = {IEEE INFOCOM, Demo session},
    month = jul,
    year = {2020},
    volume = {},
    pages = {},
    doi = {},
    howpublished = {https://nonsns.github.io/paper/rossi20infocom-b.pdf},
    topic = {tc-xai}
  }
  

  Fostered by the tremendous success in the image recognition field, recently there has been a strong push for the adoption of Convolutional Neural Networks (CNN) in networks, especially at the edge, assisted by low-power hardware equipment (known as “tensor processing units”) for the acceleration of CNN- related computations. The availability of such hardware has reignited the interest for traffic classification approaches that are based on Deep Learning. However, unlike tree-based approaches that are easy to interpret, CNNs are in essence represented by a large number of weights, whose interpretation is particularly obscure for the human operators. Since human operators will need to deal, troubleshoot, and maintain these automatically learned models, that will replace the more easily human-readable heuristic rules of DPI classification engine, there is a clear need to open the “deep pandora box”, and make it easily accessible for network domain experts. In this demonstration, we shed light in the inference process of a commercial-grade classification engine dealing with hundreds of classes, enriching the classification workflow with tools to enable better understanding of the inner mechanics of both the traffic and the models.
• [INFOCOM-20a] Navarro, Jose Manuel and Rossi, Dario, "HURRA: Human-Readable Router Anomaly Detection" IEEE INFOCOM, Demo session jul. 2020, DOI Conference Abstract Bibtex

  @inproceedings{DR:INFOCOM-20a,
    author = {Navarro, Jose Manuel and Rossi, Dario},
    title = {HURRA: Human-Readable Router Anomaly Detection},
    booktitle = {IEEE INFOCOM, Demo session},
    month = jul,
    year = {2020},
    volume = {},
    pages = {},
    doi = {},
    howpublished = {https://nonsns.github.io/paper/rossi20infocom-a.pdf},
    topic = {ad-fs}
  }
  

  Automated troubleshooting tools must be based on solid and principled algorithms to be useful. However, these tools need to be easily accessible for non-experts, thus requiring to also be usable. This demo combines both requirements by combining an anomaly detection engine inspired by Auto-ML principles, that combines multiple methods to find robust solutions, with automated ranking of results to provide an intuitive interface that is remindful of a search engine. The net result is that HURRA! simplifies as much as possible human operators interaction while providing them with the most useful results first. In the demo, we contrast manual labeling of individual features gathered from human operators from real troubleshooting tickets with results returned by the engine — showing an empirically good match at a fraction of the human labor.
• [INFOCOM-20d] , "Removing human players from the loop: AI-assisted assessment of Gaming QoE" IEEE INFOCOM, Workshop on Network Intelligence jul. 2020, Conference Abstract Bibtex

  @inproceedings{DR:INFOCOM-20d,
    title = {Removing human players from the loop: AI-assisted assessment of Gaming QoE},
    author = {},
    booktitle = {IEEE INFOCOM, Workshop on Network Intelligence},
    month = jul,
    year = {2020},
    howpublished = {https://nonsns.github.io/paper/rossi20infocom-d.pdf},
    topic = {game-qoe}
  }
  

  Quality of Experience (QoE) assessment for video games is known for being a heavy-weight process, typically requiring the active involvement of several human players and bringing limited transferability across games. Clearly, to some extent, QoE is correlated with the achieved in-game score, as player frustration will arise whenever realized performance is far from what is expected due to conditions beyond player control such as network congestion in the increasingly prevalent case of networked games. To disrupt the status quo, we propose to remove human players from the loop and instead exploit Deep Reinforcement Learning (DRL) agents to play games under varying network conditions. We apply our framework to a set of Atari games with different types of interaction, showing that the score degradation observed with DRL agents can be exploited in networking devices (e.g., by prioritizing scheduling decisions), reinforcing fairness across games, and thus enhancing the overall quality of gaming experience
• [NETWORKING-20] Huet, Alexis and Saverimoutou, Antoine and Houidi, Zied Ben and Hao Shi, Shengming Cai and Xu, Jinchun and Mathieu, Bertrand and Rossi, Dario, "Revealing QoE of Web Users from Encrypted Network Traffic" IFIP Networking jun. 2020, Conference Abstract Bibtex

  @inproceedings{DR:NETWORKING-20,
    title = {Revealing QoE of Web Users from Encrypted Network Traffic},
    author = {Huet, Alexis and Saverimoutou, Antoine and Houidi, Zied Ben and Hao Shi, Shengming Cai and Xu, Jinchun and Mathieu, Bertrand and Rossi, Dario},
    year = {2020},
    booktitle = {IFIP Networking},
    venue = {Paris},
    month = jun,
    howpublished = {https://nonsns.github.io/paper/rossi20networking.pdf},
    topic = {web-qoe}
  }
  

  Internet Service Providers (ISPs) have a lot to gain from estimating the Web browsing quality of their customers. However, unlike Content Providers (CPs) who can easily access in-browser computed application-level metrics to estimate Web browsing quality, ISPs come short mainly because of traffic encryption. In this paper, we use exact methods and machine learning to estimate well-known application-level Web browsing QoS metrics (such as SpeedIndex and Page Load Time) from raw encrypted streams of network traffic. Particularly, we present and open-source a unique dataset targeting a large set of popular pages (Alexa top-500), from probes from several ISPs networks, browsers software (Chrome, Firefox) and viewport combinations, for over 200,000 experiments. Our results show our models to be accurate, and we particularly focus on their ability to generalize to previously unseen conditions, giving guidance concerning their retraining
• [MedComNet-20] Salutari, Flavia and Varvello, Matteo and Teixeira, Renata and Christophides, Vassilis and Rossi, Dario and Hora, Diego Da, "Implications of User Perceived Page Load Time Multi-Modality on Web QoE Measurement" MedComNet jun. 2020, DOI Conference Abstract Bibtex

  @inproceedings{DR:MedComNet-20,
    author = {Salutari, Flavia and Varvello, Matteo and Teixeira, Renata and Christophides, Vassilis and Rossi, Dario and Hora, Diego Da},
    title = {Implications of User Perceived Page Load Time Multi-Modality on Web QoE Measurement},
    booktitle = {MedComNet},
    month = jun,
    year = {2020},
    volume = {},
    pages = {},
    doi = {},
    howpublished = {https://nonsns.github.io/paper/rossi20medcomnet.pdf},
    topic = {web-qoe}
  }
  

  Web browsing is one of the most popular applications for both desktop and mobile users. A lot of effort has been devoted to speedup the Web, as well as in designing metrics that can accurately tell whether a webpage loaded fast or not. An often implicit assumption made by industrial and academic research communities is that a single metric is sufficient to assess whether a webpage loaded fast. In this paper we collect and make publicly available a unique dataset which contains webpage features (eg number and type of embedded objects) along with both objective and subjective Web quality metrics. This dataset was collected by crawling over 100 websites–representative of the top 1,000,000 websites in the Web — while crowdsourcing 6,000 user opinions on user perceived page load time (uPLT). We show that the uPLT distribution is often multi-modal and that, in practice, no more than three modes are present. The main conclusion drawn from our analysis is that, for complex webpages, each of the different objective QoE metrics proposed in the literature (such as AFT, TTI, PLT, etc.) is suited to approximate one of the different uPLT modes.
• [TNSM-20a] Salutari, F. and Da Hora, D. and Dubuc, G. and Rossi, D., "Analyzing Wikipedia Users’ Perceived Quality Of Experience: A Large-Scale Study" In IEEE Transactions on Network and Service Management, Vol. 17, No. 2, pp.1082–1095, jun. 2020, DOI 10.1109/TNSM.2020.2978685 Journal Abstract Bibtex

  @article{DR:TNSM-20a,
    author = {{Salutari}, F. and {Da Hora}, D. and {Dubuc}, G. and {Rossi}, D.},
    journal = {IEEE Transactions on Network and Service Management},
    title = {Analyzing Wikipedia Users’ Perceived Quality Of Experience: A Large-Scale Study},
    year = {2020},
    month = jun,
    volume = {17},
    number = {2},
    pages = {1082--1095},
    doi = {10.1109/TNSM.2020.2978685},
    howpublished = {https://nonsns.github.io/paper/rossi20tnsm-a.pdf},
    topic = {web-qoe}
  }
  

  The Web is one of the most successful Internet applications. Yet, the quality of Web users’ experience is still largely impenetrable. Whereas Web performance is typically studied with controlled experiments, in this work we perform a large-scale study of a real site, Wikipedia, explicitly asking (a small fraction of its) users for feedback on the browsing experience. The analysis of the collected feedback reveals that 85% of users are satisfied, along with both expected (e.g., the impact of browser and network connectivity) and surprising findings (e.g., absence of day/night, weekday/weekend seasonality) that we detail in this paper. Also, we leverage user responses to build supervised data-driven models to predict user satisfaction which, despite including state-of-the art quality of experience metrics, are still far from achieving accurate results (0.62 recall of negative answers). Finally, we make our dataset publicly available, hopefully contributing in enriching and refining the scientific community knowledge on Web users’ QoE.
• [WWW-19] Salutari, Flavia and Hora, Diego Da and Dubuc, Gilles and Rossi, Dario, "A large-scale study of Wikipedia users’ Quality of Experience" The Web Conference (WWW’19) may. 2019, Conference Abstract Bibtex

  @inproceedings{DR:WWW-19,
    title = {{A large-scale study of Wikipedia users' Quality of Experience}},
    author = {Salutari, Flavia and Hora, Diego Da and Dubuc, Gilles and Rossi, Dario},
    booktitle = {The Web Conference (WWW'19)},
    month = may,
    year = {2019},
    howpublished = {https://nonsns.github.io/paper/rossi19www.pdf},
    dataseturl = {https://webqoe.telecom-paristech.fr/data/}
  }
  

  The Web is one of the most successful Internet application. Yet, the quality of Web users’ experience is still largely impenetrable. Whereas Web performances are typically gathered with controlled experiments, in this work we perform a large-scale study of one of the most popular Web sites, namely Wikipedia, explicitly asking (a small fraction of its) users for feedback on the browsing experience. We leverage user survey responses to build a data-driven model of user satisfaction which, despite including state-of-the art quality of experience metrics, is still far from achieving accurate results, and discuss directions to move forward. Finally, we aim at making our dataset publicly available, which hopefully contributes in enriching and refining the scientific community knowledge on Web users’ quality of experience (QoE).
• [INFOCOM-19b] Huet, Alexis and Rossi, Dario, "Explaining Web users’ QoE with Factorization Machines" IEEE INFOCOM apr. 2019, Conference Abstract Bibtex

  @inproceedings{DR:INFOCOM-19b,
    author = {Huet, Alexis and Rossi, Dario},
    title = {Explaining Web users' QoE with Factorization Machines},
    booktitle = {IEEE INFOCOM},
    month = apr,
    year = {2019},
    location = {Paris, France},
    howpublished = {https://nonsns.github.io/paper/rossi19infocom-b.pdf},
    demourl = {https://huet.shinyapps.io/webqoe/}
  }
  

  Whereas most of the literature employs classic machine learning techniques (such as C4.5 trees, Random Forest and Support Vector Machines) to improve forecast accuracy of QoE models, in this demo we explore the use of an information filtering system (Factorization Machine) to get fundamental insights and explain the relationship between QoE and different features.
• [SIGCOMM-19] , "Web Quality of Experience from Encrypted Packets" ACM SIGCOMM, Demo Session 2019, Conference Abstract Bibtex

  @inproceedings{DR:SIGCOMM-19,
    title = {{Web Quality of Experience from Encrypted Packets}},
    authors = {Alexis Huet and Zied Ben Houidi and Shengming Cai and Hao Shi and Jinchun Xu and Dario Rossi},
    booktitle = {{ACM SIGCOMM, Demo Session}},
    year = {2019},
    howpublished = {https://nonsns.github.io/paper/rossi19sigcomm.pdf},
    demourl = {https://huawei-webqoe.shinyapps.io/sigcommdemo/},
    videourl = {https://perso.telecom-paristech.fr/drossi/data/videos/ACM-SIGCOMM-19-webqoe-demo.mp4}
  }
  

  Pervasive encryption makes it hard for ISPs to manage their network. Yet, to avoid user churn at times of shrinking revenues, ISPs must be able to assess the quality of experience they are delivering to their customers. The case of the Web is particularly complex, with a plethora of recently proposed in-browser metrics that aim at capturing the page visual rendering quality (e.g. Above the Fold and SpeedIndex). In this demo, we showcase that such metrics can be estimated quite accurately just from streams of encrypted packets, using classic supervised learning techniques.

NewNet@Paris Chair 36

• [IEEEPROC-19] Linguaglossa, L. and Lange, S. and Pontarelli, S. and Rétvári, G. and Rossi, D. and Zinner, T. and Bifulco, R. and Jarschel, M. and Bianchi, G., "Survey of Performance Acceleration Techniques for Network Function Virtualization" In Proceedings of the IEEE, Vol. 107, No. 4, pp.746-764, apr. 2019, DOI 10.1109/JPROC.2019.2896848 Journal Abstract Bibtex

  @article{DR:IEEEPROC-19,
    author = {{Linguaglossa}, L. and {Lange}, S. and {Pontarelli}, S. and {Rétvári}, G. and {Rossi}, D. and {Zinner}, T. and {Bifulco}, R. and {Jarschel}, M. and {Bianchi}, G.},
    journal = {Proceedings of the IEEE},
    title = {Survey of Performance Acceleration Techniques for Network Function Virtualization},
    year = {2019},
    volume = {107},
    number = {4},
    pages = {746-764},
    keywords = {Acceleration;Performance evaluation;Ecosystems;Network function virtualization;Virtualization;Virtualization;Communication networks;Fast packet processing;network function virtualization (NFV);offloading;performance acceleration;virtualization},
    doi = {10.1109/JPROC.2019.2896848},
    issn = {0018-9219},
    month = apr,
    howpublished = {https://nonsns.github.io/paper/rossi19ieeeproc.pdf}
  }
  

  The ongoing network softwarization trend holds the promise to revolutionize network infrastructures by making them more flexible, reconfigurable, portable, and more adaptive than ever. Still, the migration from hard-coded/hard-wired network functions toward their software-programmable counterparts comes along with the need for tailored optimizations and acceleration techniques so as to avoid or at least mitigate the throughput/latency performance degradation with respect to fixed function network elements. The contribution of this paper is twofold. First, we provide a comprehensive overview of the host-based network function virtualization (NFV) ecosystem, covering a broad range of techniques, from low-level hardware acceleration and bump-in-the-wire offloading approaches to high-level software acceleration solutions, including the virtualization technique itself. Second, we derive guidelines regarding the design, development, and operation of NFV-based deployments that meet the flexibility and scalability requirements of modern communication networks.
• [INFOCOM-19a] Lange, Stanislav and Linguaglossa, Leonardo and Geissler, Stefan and Rossi, Dario and Zinner, Thomas, "Discrete-time modeling of NFV accelerators that exploit batched processing" IEEE INFOCOM apr. 2019, Conference Abstract Bibtex

  @inproceedings{DR:INFOCOM-19a,
    author = {Lange, Stanislav and Linguaglossa, Leonardo and Geissler, Stefan and Rossi, Dario and Zinner, Thomas},
    title = {Discrete-time modeling of {NFV} accelerators that exploit batched processing},
    booktitle = {IEEE INFOCOM},
    month = apr,
    year = {2019},
    location = {Paris, France},
    howpublished = {https://nonsns.github.io/paper/rossi19infocom-a.pdf}
  }
  

  Network Functions Virtualization (NFV) is among the latest network revolutions, bringing flexibility and avoiding network ossification. At the same time, all-software NFV implementations on commodity hardware raise performance issues with respect to ASIC solutions. To address these issues, numerous software acceleration frameworks for packet processing have appeared in the last few years. Common among these frameworks is the use of batching techniques. In this context, packets are processed in groups as opposed to individually, which is required at high-speed to minimize the framework overhead, reduce interrupt pressure, and leverage instruction-level cache hits. Whereas several system implementations have been proposed and experimentally benchmarked, the scientific community has so far only to a limited extent attempted to model the system dynamics of modern NFV routers exploiting batching acceleration. In this paper, we fill this gap by proposing a simple generic model for such batching-based mechanisms, which allows a very detailed prediction of highly relevant performance indicators. These include the distribution of the processed batch size as well as queue size, which can be used to identify loss-less operational regimes or quantify the packet loss probability in high-load scenarios. We contrast the model prediction with experimental results gathered in a high-speed testbed including an NFV router, showing that the model not only correctly captures system performance under simple conditions, but also in more realistic scenarios in which traffic is processed by a mixture of functions.
• [COMNET-19] , "High-Speed Data Plane and Network Functions Virtualization by Vectorizing Packet Processing" In Elsevier Computer Networks, Vol. 149, pp.187–199, feb. 2019, DOI https://doi.org/10.1016/j.comnet.2018.11.033 Journal Abstract Bibtex

  @article{DR:COMNET-19,
    author = {},
    title = {High-Speed Data Plane and Network Functions Virtualization by Vectorizing Packet Processing},
    journal = {Elsevier Computer Networks},
    month = feb,
    year = {2019},
    volume = {149},
    pages = {187--199},
    doi = {https://doi.org/10.1016/j.comnet.2018.11.033},
    howpublished = {https://nonsns.github.io/paper/rossi19comnet.pdf}
  }
  

  In the last decade, a number of frameworks started to appear that implement, directly in user-space with kernel-bypass mode, high-speed software data plane functionalities on commodity hardware. Vector Packet Processor (VPP) is one of such frameworks, representing an interesting point in the design space in that it offers: (i) in user-space networking, (ii) the flexibility of a modular router (Click and variants) with (iii) the benefits brought by techniques such as batch processing that have become commonplace in high-speed networking stacks (such as netmap or DPDK). Similarly to Click, VPP lets users arrange functions as a processing graph, providing a full-blown stack of network functions. However, unlike Click where the whole tree is traversed for each packet, in VPP each traversed node processes all packets in the batch (called vector ) before moving to the next node. This design choice enables several code optimizations that greatly improve the achievable processing throughput. This paper introduces the main VPP concepts and architecture, and experimentally evaluates the impact of design choices (such as batch packet processing) on its performance.
• [TNSM-19] Zhang, Tianzhu and Linguaglossa, Leonardo and Gallo, Massimo and Giaccone, Paolo and Rossi, Dario, "FloWatcher-DPDK: Lightweight line-rate flow-level monitoring in software" In IEEE Transactions on Networks and Service Management, Vol. , No. , pp., . 2019, DOI 10.1109/TNSM.2019.2913710 Journal Abstract Bibtex

  @article{DR:TNSM-19,
    author = {Zhang, Tianzhu and Linguaglossa, Leonardo and Gallo, Massimo and Giaccone, Paolo and Rossi, Dario},
    title = {{FloWatcher-DPDK: Lightweight line-rate flow-level monitoring in software}},
    journal = {IEEE Transactions on Networks and Service Management},
    year = {2019},
    volume = {},
    number = {},
    pages = {},
    keywords = {Monitoring;Tools;Software;Hardware;Generators;Loss measurement;Benchmark testing;Network traffic monitoring;high-speed packet processing;per-flow packet measurement;Intel DPDK.},
    doi = {10.1109/TNSM.2019.2913710},
    issn = {1932-4537},
    month = {},
    howpublished = {https://nonsns.github.io/paper/rossi19tnsm.pdf}
  }
  

  In the last few years, several software-based solutions have been proved to be very efficient for high-speed packet processing, traffic generation and monitoring, and can be considered valid alternatives to expensive and non-flexible hardware-based solutions. In our work, we first benchmark heterogeneous design choices for software-based packet monitoring systems in terms of achievable performance and required resources (i.e., the number of CPU cores). Building on this extensive analysis we design FloWatcher-DPDK, a DPDK-based high-speed software traffic monitor we provide to the community as an open source project. In a nutshell, FloWatcher-DPDK provides tunable fine-grained statistics at packet and flow levels. Experimental results demonstrate that FloWatcher-DPDK sustains per-flow statistics with 5-nines precision at high-speed (e.g., 14.88 Mpps) using a limited amount of resources. Finally, we showcase the usage of FloWatcher-DPDK by configuring it to analyze the performance of two open source prototypes for stateful flow-level end-host and in-network packet processing.
• [TON-19] Daly, James and Bruschi, Valerio and Linguaglossa, Leonardo and Pontarelli, Salvatore and Rossi, Dario and Tollet, Jerome and Torng, Eric and Yourtchenko, Andrew, "TupleMerge: Fast Software Packet Processing for Online Packet Classification" In IEEE Transactions on Networking, Vol. , No. , pp., 2019, DOI 10.1109/TNET.2019.2920718 Journal Abstract Bibtex

  @article{DR:TON-19,
    title = {TupleMerge: Fast Software Packet Processing for Online Packet Classification},
    doi = {10.1109/TNET.2019.2920718},
    journal = {IEEE Transactions on Networking},
    author = {Daly, James and Bruschi, Valerio and Linguaglossa, Leonardo and Pontarelli, Salvatore and Rossi, Dario and Tollet, Jerome and Torng, Eric and Yourtchenko, Andrew},
    year = {2019},
    volume = {},
    number = {},
    pages = {},
    howpublished = {https://nonsns.github.io/paper/rossi19ton.pdf}
  }
  

  Packet classification is an important part of many networking devices, such as routers and firewalls. Software Defined Networking (SDN) heavily relies on online packet classification which must efficiently process two different streams: incoming packets to classify and rules to update. This rules out many offline packet classification algorithms that do not support fast updates. We propose a novel online classification algorithm, TupleMerge (TM), derived from Tuple Space Search (TSS), the packet classifier used by Open vSwitch (OVS). TM improves upon TSS by combining hash tables which contain rules with similar characteristics. This greatly reduces classification time preserving similar performance in updates. We validate the effectiveness of TM using both simulation and deployment in an full-fledged software router, specifically within Vector Packet Processor (VPP). In our simulation results, which focus solely on the efficiency of the classification algorithm, we demonstrate that TM outperforms all other state of the art methods including TSS, PartitionSort (PS), and SAX-PAC. For example, TM is 34% faster at classifying packets and 30% faster at updating rules than PS. We then evaluate experimentally TM deployed within the VPP framework comparing TM against linear search and TSS, and also against TSS within the OVS framework. This validation of deployed implementations is important as SDN frameworks have several optimizations such as caches that may minimize the influence of a classification algorithm. Our experimental results clearly validate the effectiveness of TM. VPP TM classifies packets nearly two orders of magnitude faster than VPP TSS and at least one order of magnitude faster than OVS TSS.
• [ITC-18] Enguehard, Marcel and Carofiglio, Giovanna and Rossi, Dario, "A popularity-based approach for effective Cloud offload in Fog clusters" 30th International Teletraffic Congress (ITC30) sep. 2018, Conference Abstract Bibtex

  @inproceedings{DR:ITC-18,
    author = {Enguehard, Marcel and Carofiglio, Giovanna and Rossi, Dario},
    title = {A popularity-based approach for effective Cloud offload in Fog clusters},
    booktitle = {30th International Teletraffic Congress (ITC30)},
    month = sep,
    location = {Vienna, Austria},
    year = {2018},
    howpublished = {https://nonsns.github.io/paper/rossi18itc.pdf}
  }
  

  Recent research has put forward the concept of Fog computing, a deported intelligence for IoT networks. Fog clusters are meant to complement current cloud deployments, providing compute and storage resources directly in the access network – which is particularly useful for low-latency applications. How- ever, Fog deployments are expected to be less elastic than cloud platforms, since elasticity in Cloud platforms comes from the scale of the data-centers. Thus, a Fog node dimensioned for the average traffic load of a given application will not be able to handle sudden bursts of traffic. In this paper, we explore such a use-case, where a Fog-based latency-sensitive application must offload some of its processing to the Cloud. We build an analytical queueing model for deriving the statistical response time of a Fog deployment under different request Load Balancing (LB) strategies, contrasting a naive, an ideal (LFU-LB, assuming a priori knowledge of the request popularity) and a practical (LRU-LB, based on online learning of the popularity with an LRU filter) scheme. Using our model, and confirming the results through simulation, we show that our LRU-LB proposal achieves close-to-ideal performance, with high savings on Cloud offload cost with respect to a request-oblivious strategy in the explored scenarios.
• [BIGDAMA-18] Putina, Andrian and Rossi, Dario and Bifet, Albert and Barth, Steven and Pletcher, Drew and Precup, Cristina and Nivaggioli, Patrice, "Telemetry-based stream-learning of BGP anomalies" ACM SIGCOMM Workshop on Big Data Analytics and Machine Learning for Data Communication Networks (Big-DAMA’18) aug. 2018, Conference Abstract Bibtex

  @inproceedings{DR:BIGDAMA-18,
    author = {Putina, Andrian and Rossi, Dario and Bifet, Albert and Barth, Steven and Pletcher, Drew and Precup, Cristina and Nivaggioli, Patrice},
    title = {Telemetry-based stream-learning of BGP anomalies},
    booktitle = {ACM SIGCOMM Workshop on Big Data Analytics and Machine Learning for Data Communication Networks (Big-DAMA'18)},
    month = aug,
    year = {2018},
    location = {Budapest, Hungary},
    howpublished = {https://nonsns.github.io/paper/rossi18bigdama.pdf}
  }
  

  Recent technology evolution allows network equipments to continuously stream a wealth of "telemetry" information, which pertains to multiple protocols and layers of the tack, at a very fine spatial-grain and high-frequency. Processing this deluge of telemetry data in real-time clearly offers new opportunities for network control and troubleshooting, but also poses serious challenges. We tackle this challenge by applying streaming machine-learning techniques to the continuous flow of control and data-plane telemetry data, with the purpose of real-time detection of BGP anomalies. In particular, we implement an anomaly detection engine that leverages DenStream, an unsupervised clustering technique, and apply it to features collected from a large-scale testbed comprising tens of routers traversed by 1 Terabit/s worth of real application traffic. In spirit with the recent trend toward reproducibility of research results, we make our code and datasets available as open source to the scientific community
• [JSAC-18] Tortelli, Michele and Rossi, Dario and Leonardi, Emilio, "Parallel Simulation of Very Large-Scale General Cache Networks" In IEEE Journal on Selected Areas in Communication (JSAC), Vol. 36, pp.1871–1886, aug. 2018, DOI 10.1109/JSAC.2018.2844938 Journal Abstract Bibtex

  @article{DR:JSAC-18,
    title = {Parallel Simulation of Very Large-Scale General Cache Networks},
    author = {Tortelli, Michele and Rossi, Dario and Leonardi, Emilio},
    year = {2018},
    journal = {IEEE Journal on Selected Areas in Communication (JSAC)},
    volume = {36},
    month = aug,
    pages = {1871--1886},
    howpublished = {https://nonsns.github.io/paper/rossi18jsac.pdf},
    doi = {10.1109/JSAC.2018.2844938}
  }
  

  In this paper we propose a methodology for the study of general cache networks, which is intrinsically scalable and amenable to parallel execution. We contrast two techniques: one that slices the network, and another that slices the content catalog. In the former, each core simulates requests for the whole catalog on a subgraph of the original topology, whereas in the latter each core simulates requests for a portion of the original catalog on a replica of the whole network. Interestingly, we find out that when the number of cores increases (and so the split ratio of the network topology), the overhead of message passing required to keeping consistency among nodes actually offsets any benefit from the parallelization: this is strictly due to the correlation among neighboring caches, meaning that requests arriving at one cache allocated on one core may depend on the status of one or more caches allocated on different cores. Even more interestingly, we find out that the newly proposed catalog slicing, on the contrary, achieves an ideal speedup in the number of cores. Overall, our system, which we make available as open source software, enables performance assessment of large-scale general cache networks, i.e., comprising hundreds of nodes, trillions contents, and complex routing and caching algorithms, in minutes of CPU time and with exiguous amounts of memory.
• [SIGCOMM-18a] da Hora, Diego Neves and Rossi, Dario and Christophides, Vassilis and Teixeira, Renata, "A practical method for measuring Webabove-the-fold time" ACM SIGCOMM, Demo Session aug. 2018, Conference Abstract Bibtex

  @inproceedings{DR:SIGCOMM-18a,
    title = {A practical method for measuring Webabove-the-fold time},
    author = {da Hora, Diego Neves and Rossi, Dario and Christophides, Vassilis and Teixeira, Renata},
    booktitle = {ACM SIGCOMM, Demo Session},
    address = {Budapest, Hungary},
    month = aug,
    year = {2018},
    howpublished = {https://nonsns.github.io/paper/rossi18sigcomm-a.pdf}
  }
  

  Page load time (PLT) is still the most common application Quality of Service (QoS) metric to estimate the Quality of Experience (QoE) of Web users. Yet, recent literature abounds with interesting proposals for alternative metrics (e.g., Above The Fold, SpeedIndex and variants) that aim at closely capturing how users perceive the Webpage rendering process. However, these novel metrics are typically computationally expensive, as they require to monitor and post-process videos of the rendering process, and have failed to be widely deployed. In this demo, we show our implementation of an open-source Chrome extension that implements a practical and lightweight method to measure the approximated Above-the-Fold (AATF) time, as well as others Web performance metrics. The idea is, instead of accurately monitoring the rendering output, to track the download time of the last visible object on screen (i.e., “above the fold”). Our plugin also has options to save detailed reports for later analysis, a functionality ideally suited for researchers wanting to gather data from Web experiments.
• [SIGCOMM-18c] Addanki, Vamsi and Linguaglossa, Leonardo and Roberts, James and Rossi, Dario, "Fair dropping for multi-resource fairness in software routers" aug. 2018, Bookch Abstract Bibtex

  @inbook{DR:SIGCOMM-18c,
    author = {Addanki, Vamsi and Linguaglossa, Leonardo and Roberts, James and Rossi, Dario},
    title = {Fair dropping for multi-resource fairness in software routers},
    booktitle = {ACM SIGCOMM, Demo Session},
    address = {Budapest, Hungary},
    month = aug,
    year = {2018},
    howpublished = {https://nonsns.github.io/paper/rossi18sigcomm-c.pdf}
  }
  

  We demonstrate that fair dropping is an effective means to realize fair sharing of bandwidth and CPU in a software router. Analysis underpinning the effectiveness of the proposed approach is presented in an IFIP Networking 2018 paper [1]
• [SIGCOMM-18b] Zhang, Tianzhu and Linguaglossa, Leonardo and Gallo, Massimo and Giaccone, Paolo and Rossi, Dario, "FlowMon-DPDK: Parsimonious per-flow software monitoring at line rate" ACM SIGCOMM, Demo Session aug. 2018, Conference Abstract Bibtex

  @inproceedings{DR:SIGCOMM-18b,
    author = {Zhang, Tianzhu and Linguaglossa, Leonardo and Gallo, Massimo and Giaccone, Paolo and Rossi, Dario},
    title = {FlowMon-DPDK: Parsimonious per-flow software monitoring at line rate},
    booktitle = {ACM SIGCOMM, Demo Session},
    address = {Budapest, Hungary},
    month = aug,
    year = {2018},
    howpublished = {https://nonsns.github.io/paper/rossi18sigcomm-b.pdf}
  }
  

  Software packet processing is an intriguing approach due to its tremendous flexibility and cost reduction compared with hardware solutions, which have long dominated software performance. However, the emergence of fast packet I/O frameworks challenges hardware supremacy, as software solutions based on commodity hardware manage to process packets at high speed (10-40 Gbps). Whereas novel packet processing applications based on these new frameworks proliferate, fine-grained traffic monitor at high speed has received comparatively less attention. In this demonstration, we showcase FlowMon-DPDK a novel software traffic monitor recently published at TMA 2018, based on the Intel DPDK I/O framework. Our monitor is capable of providing runtime statistics at both packet- and flow-levels at 10 Gbit/s using a minimal amount of CPU resources, with packet losses that are order of magnitude smaller than state-of-the-art software. A video showing the demonstration is available at \urlhttps://youtu.be/B8uaw9UgMm0. For further details, please refer to our TMA 2018 paper.
• [HPSR-18] Gong, YiXi and Roberts, James W. and Rossi, Dario, "Per-Flow Fairness in the Datacenter Network" IEEE International Conference on High Performance Switching and Routing (HPSR’18) jun. 2018, Conference Abstract Bibtex

  @inproceedings{DR:HPSR-18,
    author = {Gong, YiXi and Roberts, James W. and Rossi, Dario},
    title = {Per-Flow Fairness in the Datacenter Network},
    booktitle = {IEEE International Conference on High Performance Switching and Routing (HPSR'18)},
    month = jun,
    year = {2018},
    location = {Bucharest, Romania},
    howpublished = {https://nonsns.github.io/paper/rossi18hpsr.pdf}
  }
  

  Datacenter network (DCN) design has been actively researched for over a decade. Solutions proposed range from end-to-end transport protocol redesign to more intricate, monolithic and cross-layer architectures. Despite this intense activity, to date we remark the absence of DCN proposals based on simple fair scheduling strategies. In this paper, we evaluate the effectiveness of FQ-CoDel in the DCN environment. Our results show, (i) that average throughput is greater than that attained with DCN tailored protocols like DCTCP, and (ii) the completion time of short flows is close to that of state-of-art DCN proposals like pFabric. Good enough performance and striking simplicity make FQ-CoDel a serious contender in the DCN arena.
• [NOSSDAV-18] Samain, Jacques and Carofiglio, Giovanna and Tortelli, Michele and Rossi, Dario, "A simple yet effective network-assisted signal for enhanced DASH quality of experience" 28th ACM SIGMM Workshop on Network and Operating Systems Support for Digital Audio and Video (NOSSDAV’18) jun. 2018, Conference Award Abstract Bibtex

  @inproceedings{DR:NOSSDAV-18,
    author = {Samain, Jacques and Carofiglio, Giovanna and Tortelli, Michele and Rossi, Dario},
    title = {A simple yet effective network-assisted signal for enhanced DASH quality of experience},
    booktitle = {28th ACM SIGMM Workshop on Network and Operating Systems Support for Digital Audio and Video (NOSSDAV'18)},
    month = jun,
    year = {2018},
    note = {bestpaperaward},
    howpublished = {https://nonsns.github.io/paper/rossi18nossdav.pdf}
  }
  

  propose and evaluate simple signals coming from in-network telemetry that are effective to enhance the quality of DASH streaming. Specifically, in-network caching is known to positively affect DASH streaming quality but at the same time negatively affect the controller stability, increasing the quality switch ratio. Our contributions are to first (i) consider the broad spectrum of interaction between the network and the application, and then (ii) to devise how to effectively exploit in a DASH controller a very simple signal (i.e., per-quality hit ratio) that can be exported by framework such as Server and Network Assisted DASH (SAND) at fairly low rate (i.e., a timescale of 10s of seconds). Our thorough experimental campaign confirms the soundness of the approach (that significantly ameliorate performance with respect to network-blind DASH), as well as its robustness (i.e., tuning is not critical) and practical appeal (i.e., due to its simplicity and compatibility with SAND).
• [QOMEX-18] Hossfeld, Tobias and Metzger, Florian and Rossi, Dario, "Speed Index: Relating the Industrial Standard for User Perceived Web Performance to Web QoE" 10th International Conference on Quality of Multimedia Experience (QoMEX 2018) jun. 2018, Conference Abstract Bibtex

  @inproceedings{DR:QOMEX-18,
    author = {Hossfeld, Tobias and Metzger, Florian and Rossi, Dario},
    title = {Speed Index: Relating the Industrial Standard for User Perceived Web Performance to Web QoE},
    booktitle = {10th International Conference on Quality of Multimedia Experience (QoMEX 2018)},
    month = jun,
    year = {2018},
    location = {Sardinia, Italy},
    howpublished = {https://nonsns.github.io/paper/rossi18qomex.pdf}
  }
  

  In 2012, Google introduced the Speed Index (SI) metric to quantify the speed of the Web page visual completeness for the actually displayed above-the-fold (ATF) portion of a Web page. In Web browsing a page might appear to the user to be already fully rendered, even though further content may still be retrieved, resulting in the Page Load Time (PLT). This happens due to the browser progressively rendering all objects, part of which can also be located below the browser window’s current viewport. The SI metric (and variants) thereof have since established themselves as a de facto standard in Web page and browser testing. While SI is a step in the direction of including the user experience into Web metrics, the actual meaning of the metric and especially its relationship between Speed Index and Web QoE is however far from being clear. The contributions of this paper are thus to first develop an understanding of the SI based on a theoretical analysis and second, to analyze the interdependency between SI and MOS values from an existing public dataset. Specifically, our analysis is based on two well established models that map the user waiting time to a user ACR-rating of the QoE. The analysis show that ATF-based metrics are more appropriate than pure PLT as input to Web QoE models.
• [TMA-18] Zhang, Tianzhu and Linguaglossa, Leonardo and Gallo, Massimo and Giaccone, Paolo and Rossi, Dario, "FlowMon-DPDK: Parsimonious per-flow software monitoring at line rate" Network Traffic Measurement and Analysis Conference (TMA’18) jun. 2018, Conference Abstract Bibtex

  @inproceedings{DR:TMA-18,
    author = {Zhang, Tianzhu and Linguaglossa, Leonardo and Gallo, Massimo and Giaccone, Paolo and Rossi, Dario},
    title = {FlowMon-DPDK: Parsimonious per-flow software monitoring at line rate},
    booktitle = {Network Traffic Measurement and Analysis Conference (TMA'18)},
    month = jun,
    year = {2018},
    location = {Wien, Austria},
    howpublished = {https://nonsns.github.io/paper/rossi18tma.pdf}
  }
  

  Testing experimental network devices requires deep performance analysis, which is usually performed with expensive, not flexible, hardware equipment. With the advent of high- speed packet I/O frameworks, general purpose equipments have narrowed the performance gap in respect of dedicated hardware and a variety of software-based solutions have emerged for handling traffic at very high speed. While the literature abounds with software traffic generators, existing monitoring solutions do not target worst-case scenarios (i.e., 64B packets at line rate) that are particularly relevant for stress-testing high-speed network functions, or occupy too many resources. In this paper we first analyze the design space for high-speed traffic monitoring that leads us to specific choices characterizing FlowMon-DPDK, a DPDK-based software traffic monitor that we make available as open source software. In a nutshell, FlowMon-DPDK provides tunable fine-grained statistics at both packet and flow levels. Experimental results demonstrate that our traffic monitor is able to provide per-flow statistics with 5-nines precision at high-speed (14.88 Mpps) using a exiguous amount of resources. Finally, we showcase FlowMon-DPDK usage by testing two open source prototypes for stateful flow-level end-host and in-network packet processing.
• [RIPE-76] da Hora, Diego Neves and Christophides, Vassilis and Teixeira, Renata and Rossi, Dario, "Perceptual evaluation of web-browsing" Talk at the RIPE76, Measurement and Tools (MAT) Working Group may. 2018, Conference Bibtex

  @inproceedings{DR:RIPE-76,
    title = {Perceptual evaluation of web-browsing},
    author = {da Hora, Diego Neves and Christophides, Vassilis and Teixeira, Renata and Rossi, Dario},
    booktitle = {Talk at the RIPE76, Measurement and Tools (MAT) Working Group},
    address = {Marseille, France},
    month = may,
    year = {2018},
    howpublished = {}
  }
  
• [NETWORKING-18] Vamsi Addanki, Leonardo Linguaglossa, James Roberts and Rossi, Dario, "Controlling software router resource sharing by fair packet dropping" may. 2018, Conference Abstract Bibtex

  @inproceedings{DR:NETWORKING-18,
    author = {Vamsi Addanki, Leonardo Linguaglossa, James Roberts and Rossi, Dario},
    title = {Controlling software router resource sharing by fair packet dropping},
    month = may,
    location = {Zurich, Switzerland},
    year = {2018},
    howpublished = {https://nonsns.github.io/paper/rossi18networking.pdf}
  }
  

  The paper discusses resource sharing in a software router where both bandwidth and CPU may be bottlenecks. We propose a novel fair dropping algorithm to realize per-flow max-min fair sharing of these resources. The algorithm is compatible with features like batch I/O and batch processing that tend to make classical scheduling impractical. We describe an implementation using Vector Packet Processing, part of the Linux Foundation FD.io project. Preliminary experimental results prove the efficiency of the algorithm in controlling bandwidth and CPU sharing at high speed. Performance in dynamic traffic is evaluated using analysis and simulation, demonstrating that the proposed approach is both effective and scalable.
• [INFOCOM-18a] Putina, Andrian and Rossi, Dario and Bifet, Albert and Barth, Steven and Pletcher, Drew and Precup, Cristina and Nivaggioli, Patrice, "Unsupervised real-time detection of BGP anomalies leveraging high-rate and fine-grained telemetry data" IEEE INFOCOM, Demo Session apr. 2018, Conference Abstract Bibtex

  @inproceedings{DR:INFOCOM-18a,
    author = {Putina, Andrian and Rossi, Dario and Bifet, Albert and Barth, Steven and Pletcher, Drew and Precup, Cristina and Nivaggioli, Patrice},
    title = {Unsupervised real-time detection of BGP anomalies leveraging high-rate and fine-grained telemetry data},
    booktitle = {IEEE INFOCOM, Demo Session},
    month = apr,
    year = {2018},
    location = {Honolulu, Hawaii},
    howpublished = {https://nonsns.github.io/paper/rossi18infocom-a.pdf}
  }
  

  Recent technology evolution of network equipment allow to continuously stream a wealth of information, pertaining to multiple protocols and layers of the stack, at a very fine spatial-grain and at furthermore high-frequency. Processing this deluge of telemetry data in real-time clearly offers new opportunities for network control and troubleshooting, but also poses serious challenges. In this demonstration, we tackle this challenge by applying streaming machine-learning techniques to the continuous flow of control and data-plane telemetry data, with the purpose of real-time detection of BGP anomalies. In particular, we implement an anomaly detection engine that leverages DenStream, an unsupervised clustering technique, and apply it to telemetry features collected from a large-scale testbed comprising tens of routers traversed by 1 Terabit/s worth of real application traffic.
• [INFOCOM-18b] Barach, David and Linguaglossa, Leonardo and Marion, Damjan and Pfister, Pierre and Pontarelli, Salvatore and Rossi, Dario and Tollet, Jerome, "Batched packet processing for high-speed software data plane functions" IEEE INFOCOM, Demo Session apr. 2018, Conference Abstract Bibtex

  @inproceedings{DR:INFOCOM-18b,
    author = {Barach, David and Linguaglossa, Leonardo and Marion, Damjan and Pfister, Pierre and Pontarelli, Salvatore and Rossi, Dario and Tollet, Jerome},
    title = {Batched packet processing for high-speed software data plane functions},
    booktitle = {IEEE INFOCOM, Demo Session},
    month = apr,
    year = {2018},
    location = {Honolulu, Hawaii},
    howpublished = {https://nonsns.github.io/paper/rossi18infocom-b.pdf}
  }
  

  In the last decade, a number of frameworks started to appear that implement, directly in user-space with kernel-bypass mode, high-speed software data plane functionalities on commodity hardware. Vector Packet Processor (VPP) is one of such frameworks, representing an interesting point in the design space in that it offers: (i) in user-space networking, (ii) the flexibility of a modular router (Click and variants) with (iii) the benefits brought by techniques such as batch processing that have become commonplace in lower-level building blocks of high-speed networking stacks (such as netmap or DPDK). Similarly to Click, VPP lets users arrange functions as a processing graph, providing a full-blown stack of network functions. However, unlike Click where the whole tree is traversed for each packet, in VPP each traversed node processes all packets in the batch before moving to the next node. This design choice enables several code optimizations that greatly improve the achievable processing throughput: the purpose of this demonstration is to introduce the main VPP concepts and architecture, as well as experimentally showing the impact of design choices –and especially of batch packet processing–, on the achievable packet forwarding performance.
• [PAM-18a] Salutari, Flavia and Cicalese, Danilo and Rossi, Dario, "A closer look at IP-ID behavior in the Wild" International Conference on Passive and Active Network Measurement (PAM) mar. 2018, Conference Abstract Bibtex

  @inproceedings{DR:PAM-18a,
    title = {A closer look at IP-ID behavior in the Wild},
    author = {Salutari, Flavia and Cicalese, Danilo and Rossi, Dario},
    booktitle = {International Conference on Passive and Active Network Measurement (PAM)},
    address = {Berlin, Germany},
    year = {2018},
    month = mar,
    howpublished = {https://nonsns.github.io/paper/rossi18pam-a.pdf}
  }
  

  Originally used to assist network-layer fragmentation and reassembly, the IP identification field (IP-ID) has been used and abused for a range of tasks, from counting hosts behind NAT, to detect router aliases and, lately, to assist detection of censorship in the Internet at large. These inferences have been possible since, in the past, the IP- ID was mostly implemented as a simple packet counter: however, this behavior has been discouraged for security reasons and other policies, such as random values, have been suggested. In this study, we propose a framework to classify the different IP-ID behaviors using active probing from a single host. Despite being only minimally intrusive, our technique is significantly accurate (99% true positive classification) robust against packet losses (up to 20%) and lightweight (few packets suffices to discriminate all IP-ID behaviors). We then apply our technique to an Internet-wide census, where we actively probe one alive target per each routable /24 subnet: we find that that the majority of hosts adopts a constant IP-IDs (39%) or local counter (34%), that the fraction of global counters (18%) significantly diminished, that a non marginal number of hosts have an odd behavior (7%) and that random IP-IDs are still an exception (2%).
• [PAM-18b] da Hora, Diego Neves and Asrese, Alemnew Sheferaw and Christophides, Vassilis and Teixeira, Renata and Rossi, Dario, "Narrowing the gap between QoS metrics and Web QoE using Above-the-fold metrics" International Conference on Passive and Active Network Measurement (PAM), Receipient of the Best dataset award mar. 2018, Conference Award Abstract Bibtex

  @inproceedings{DR:PAM-18b,
    title = {Narrowing the gap between QoS metrics and Web QoE using Above-the-fold metrics},
    author = {da Hora, Diego Neves and Asrese, Alemnew Sheferaw and Christophides, Vassilis and Teixeira, Renata and Rossi, Dario},
    booktitle = {International Conference on Passive and Active Network Measurement (PAM), Receipient of the Best dataset award},
    address = {Berlin, Germany},
    month = mar,
    year = {2018},
    note = {bestpaperaward},
    howpublished = {https://nonsns.github.io/paper/rossi18pam-b.pdf}
  }
  

  Page load time (PLT) is still the most common application Quality of Service (QoS) metric to estimate the Quality of Experience (QoE) of Web users. Yet, recent literature abounds with proposals for alternative metrics (e.g., Above The Fold, SpeedIndex and their variants) that aim at better estimating user QoE. The main purpose of this work is thus to thoroughly investigate a mapping between established and recently proposed objective metrics and user QoE. We obtain ground truth QoE via user experiments where we collect and analyze 3,400 Web accesses annotated with QoS metrics and explicit user ratings in a scale of 1 to 5, which we make available to the community. In particular, we contrast domain expert models (such as ITU-T and IQX) fed with a single QoS metric, to models trained using our ground-truth dataset over multiple QoS metrics as features. Results of our experiments show that, albeit very simple, expert models have a comparable accuracy to machine learning approaches. Furthermore, the model accuracy improves considerably when building per-page QoE models, which may raise scalability concerns as we discuss.
• [CCR-18] Cicalese, Danilo and Rossi, Dario, "A longitudinal study of IP Anycast" In ACM Computer Communication Review, Vol. 1, 2018, Journal Abstract Bibtex

  @article{DR:CCR-18,
    title = {A longitudinal study of IP Anycast},
    author = {Cicalese, Danilo and Rossi, Dario},
    journal = {ACM Computer Communication Review},
    volume = {1},
    year = {2018},
    howpublished = {https://nonsns.github.io/paper/rossi18ccr.pdf}
  }
  

  IP anycast is a commonly used technique to share the load of a variety of global services. For more than one year, leveraging a lightweight technique for IP anycast detection, enumeration and geolocation, we perform regular IP monthly censuses. This paper provides a brief longitudinal study of the anycast ecosystem, and we additionally make all our datasets (raw measurements from PlanetLab and RIPE Atlas), results (monthly geolocated anycast replicas for all IP/24) and code available to the community.
• [TON-18] Araldo, Andrea and Dan, Gyorgy and Rossi, Dario, "Caching Encrypted Content via Stochastic Cache Partitioning" In IEEE/ACM Transactions on Networking, Vol. 26, 2018, DOI 10.1109/TNET.2018.2793892 Journal Abstract Bibtex

  @article{DR:TON-18,
    title = {Caching Encrypted Content via Stochastic Cache Partitioning},
    author = {Araldo, Andrea and Dan, Gyorgy and Rossi, Dario},
    year = {2018},
    volume = {26},
    issue = {1},
    doi = {10.1109/TNET.2018.2793892},
    journal = {IEEE/ACM Transactions on Networking},
    howpublished = {https://nonsns.github.io/paper/rossi18ton.pdf}
  }
  

  In-network caching is an appealing solution to cope with the increasing bandwidth demand of video, audio and data transfer over the Internet. Nonetheless, in order to protect consumer privacy and their own business, Content Providers (CPs) increasingly deliver encrypted content, thereby preventing Internet Service Providers (ISPs) from employing traditional caching strategies, which require the knowledge of the objects being transmitted. To overcome this emerging tussle between security and effi- ciency, in this paper we propose an architecture in which the ISP partitions the cache space into slices, assigns each slice to a different CP, and lets the CPs remotely manage their slices. This architecture enables transparent caching of encrypted content, and can be deployed in the very edge of the ISP’s network (i.e., base stations, femtocells), while allowing CPs to maintain exclusive control over their content. We propose an algorithm, called SDCP, for partitioning the cache storage into slices so as to maximize the bandwidth savings provided by the cache. A distinctive feature of our algorithm is that ISPs only need to measure the aggregated miss rates of each CP, but they need not know of the individual objects that are requested. We prove that the SDCP algorithm converges to a partitioning that is close to the optimal, and we bound its optimality gap. We use simulations to evaluate SDCP’s convergence rate under stationary and non-stationary content popularity. Finally, we show that SDCP significantly outperforms traditional reactive caching techniques, considering both CPs with perfect and with imperfect knowledge of their content popularity.
• [PARALLEL-CACHE-17] Tortelli, Michele and Rossi, Dario and Leonardi, Emilio, "Parallel Simulation of Very Large-Scale General Cache Networks" Telecom ParisTech nov. 2017, Tech.Rep. Bibtex

  @techreport{DR:PARALLEL-CACHE-17,
    title = {Parallel Simulation of Very Large-Scale General Cache Networks},
    author = {Tortelli, Michele and Rossi, Dario and Leonardi, Emilio},
    year = {2017},
    month = nov,
    institution = {Telecom ParisTech},
    howpublished = {https://nonsns.github.io/paper/drossi17parallel-cache.pdf}
  }
  
• [IPID-17] Salutari, Flavia and Cicalese, Danilo and Rossi, Dario, "A closer look at IP-ID behavior in the Wild" Telecom ParisTech oct. 2017, Tech.Rep. Bibtex

  @techreport{DR:IPID-17,
    title = {A closer look at IP-ID behavior in the Wild},
    author = {Salutari, Flavia and Cicalese, Danilo and Rossi, Dario},
    institution = {Telecom ParisTech},
    month = oct,
    year = {2017},
    pages = {},
    topic = {passivemeasurement},
    howpublished = {https://nonsns.github.io/paper/rossi17ipid.pdf}
  }
  
• [ATF-17] da Hora, Diego Neves and Asrese, Alemnew Sheferaw and Christophides, Vassilis and Teixeira, Renata and Rossi, Dario, "Narrowing the gap between QoS metrics and Web QoE using Above-the-fold metrics" Telecom ParisTech oct. 2017, Tech.Rep. Bibtex

  @techreport{DR:ATF-17,
    title = {Narrowing the gap between QoS metrics and Web QoE using Above-the-fold metrics},
    author = {da Hora, Diego Neves and Asrese, Alemnew Sheferaw and Christophides, Vassilis and Teixeira, Renata and Rossi, Dario},
    institution = {Telecom ParisTech},
    month = oct,
    year = {2017},
    topic = {qoe,measurement},
    howpublished = {https://nonsns.github.io/paper/rossi17atf.pdf}
  }
  
• [TMM-17] Samain, Jacques and Carofiglio, Giovanna and Muscariello, Luca and Papalini, Michele and Sardara, Mauro and Tortelli, Michele and Rossi, Dario, "Dynamic Adaptive Video Streaming: Towards a systematic comparison of ICN and TCP/IP" In IEEE Transactions on Multimedia, Vol. 19, pp.2166-2181, oct. 2017, DOI 10.1109/TMM.2017.2733340 Journal Abstract Bibtex

  @article{DR:TMM-17,
    title = {Dynamic Adaptive Video Streaming: Towards a systematic comparison of ICN and TCP/IP},
    author = {Samain, Jacques and Carofiglio, Giovanna and Muscariello, Luca and Papalini, Michele and Sardara, Mauro and Tortelli, Michele and Rossi, Dario},
    journal = {IEEE Transactions on Multimedia},
    volume = {19},
    issue = {10},
    month = oct,
    year = {2017},
    doi = {10.1109/TMM.2017.2733340},
    pages = {2166-2181},
    topic = {qoe,icn,streaming},
    howpublished = {https://nonsns.github.io/paper/rossi17tmm.pdf}
  }
  

  Streaming of video contents over the Internet is experiencing an unprecedented growth. While video permeates every application, it also puts tremendous pressure in the network – to support users having heterogeneous accesses and expecting high quality of experience, in a furthermore cost-effective manner. In this context, Future Internet (FI) paradigms, such as Information Centric Networking (ICN), are particularly well suited to not only enhance video delivery at the client (as in the DASH approach), but to also naturally and seamlessly extend video support deeper in the network functions. In this paper, we contrast ICN and TCP/IP with an experimental approach, where we employ several state-of-the-art DASH controllers (PANDA, AdapTech, and BOLA) on an ICN vs TCP/IP network stack. Our campaign, based on tools which we developed and made available as open-source software, includes multiple clients (homogeneous vs heterogeneous mixture, synchronous vs asynchronous arrivals), videos (up to 4K resolution), channels (e.g., DASH profiles, emulated WiFi and LTE, real 3G/4G traces), and levels of integration with an ICN network (i.e., vanilla NDN, wireless loss detection and recovery at the access point, load balancing). Our results clearly illustrate, as well as quantitatively assess, benefits of ICN-based streaming, warning about potential pitfalls that are however easy to avoid.
• [COMNET-17b] Mansilha, R. and Barcellos, M. and Leonardi, E. and Rossi, D., "Exploiting Parallelism in Hierarchical Content Stores for High-speed ICN Routers" In Elsevier Computer Networks, Vol. 125, pp.132–145, sep. 2017, DOI 10.1016/j.comnet.2017.04.041 Journal Abstract Bibtex

  @article{DR:COMNET-17b,
    title = {Exploiting Parallelism in Hierarchical Content Stores for High-speed ICN Routers},
    author = {Mansilha, R. and Barcellos, M. and Leonardi, E. and Rossi, D.},
    journal = {Elsevier Computer Networks},
    month = sep,
    year = {2017},
    doi = {10.1016/j.comnet.2017.04.041},
    pages = {132--145},
    volume = {125},
    howpublished = {https://nonsns.github.io/paper/rossi17comnet-b.pdf}
  }
  

  Information-centric network (ICN) is a novel architecture identifying data as a first class citizen, and caching as a prominent low-level feature. Yet, efficiently using large storage (e.g., 1 TB) at line rate (e.g., 10 Gbps) is not trivial: in our previous work, we proposed an ICN router design equipped with hierarchical caches, that exploits peculiarities of the ICN traffic arrival process. In this paper, we implement such proposal in the NDN Forwarding Daemon (NFD), and carry on a thorough experimental evaluation of its performance with an emulation methodology on common off the shelf hardware. Our study testifies the interest and feasibility of the approach.
• [COMNET-17a] Tortelli, Michele and Rossi, Dario and Leonardi, Emilio, "A Hybrid Methodology for the Performance Evaluation of Internet-scale Cache Networks" In Elsevier Computer Networks, Vol. 125, pp.146–159, sep. 2017, Journal Abstract Bibtex

  @article{DR:COMNET-17a,
    title = {A Hybrid Methodology for the Performance Evaluation of Internet-scale Cache Networks},
    author = {Tortelli, Michele and Rossi, Dario and Leonardi, Emilio},
    year = {2017},
    month = sep,
    journal = {Elsevier Computer Networks},
    pages = {146--159},
    volume = {125},
    howpublished = {https://nonsns.github.io/paper/rossi17comnet-a.pdf}
  }
  

  Two concurrent factors challenge the evaluation of large-scale cache networks: complex algorithmic interactions, which are hardly represented by analytical models, and catalog/network size, which limits the scalability of event-driven simulations. To solve these limitations, we propose a new hybrid technique, that we colloquially refer to as ModelGraft, which combines elements of stochastic analysis within a simulative Monte-Carlo approach. In ModelGraft, large scenarios are mapped to a downscaled counterpart built upon Time-To-Live (TTL) caches, to achieve CPU and memory scalability. Additionally, a feedback loop ensures convergence to a consistent state, whose performance accurately represent those of the original system. Finally, the technique also retains simulation simplicity and flexibility, as it can be seamlessly applied to numerous forwarding, meta-caching, and replacement algorithms. We implement and make ModelGraft available as an alternative simulation engine of ccnSim. Performance evaluation shows that, with respect to classic event-driven simulation, ModelGraft gains over two orders of magnitude in both CPU time and memory complexity, while limiting accuracy loss below 2%. Ultimately, ModelGraft pushes the boundaries of the performance evaluation well beyond the limits achieved in the current state of the art, enabling the study of Internet-scale scenarios with content catalogs comprising hundreds billions objects.
• [LONGITUDINAL-17] Cicalese, Danilo and Rossi, Dario, "A longitudinal study of IP Anycast" Telecom ParisTech jul. 2017, Tech.Rep. Bibtex

  @techreport{DR:LONGITUDINAL-17,
    title = {A longitudinal study of IP Anycast},
    author = {Cicalese, Danilo and Rossi, Dario},
    institution = {Telecom ParisTech},
    month = jul,
    year = {2017},
    howpublished = {https://nonsns.github.io/paper/rossi17longitudinal.pdf}
  }
  
• [PAM-17] Bocchi, Enrico and De Cicco, Luca and Mellia, Marco and Rossi, Dario, "The Web, the Users, and the MOS: Influence of HTTP/2 on User Experience" Passive and Active Measurements apr. 2017, Conference Abstract Bibtex

  @inproceedings{DR:PAM-17,
    title = {The Web, the Users, and the MOS: Influence of HTTP/2 on User Experience},
    author = {Bocchi, Enrico and De Cicco, Luca and Mellia, Marco and Rossi, Dario},
    year = {2017},
    month = apr,
    booktitle = {Passive and Active Measurements},
    halid = {hal-01613491},
    howpublished = {https://nonsns.github.io/paper/rossi17pam.pdf}
  }
  

  This work focuses on the evaluation of Web quality of experience as perceived by actual users and in particular on the impact of HTTP/1 vs HTTP/2. We adopt an experimental methodology that uses real web pages served through a realistic testbed where we control network, protocol, and application configuration. Users are asked to browse such pages and provide their subjective feedback, which we leverage to obtain the Mean Opinion Score (MOS), while the testbed records objective metrics. The collected dataset comprises over 4,000 grades that we explore to tackle the question whether HTTP/2 improves users experience, to what extent, and in which conditions. Findings show that users report marginal differences, with 22%, 52%, 26% of HTTP/2 MOS being better, identical, or worse than HTTP/1, respectively. Even in scenarios that favor HTTP/2, results are not as sharp as expected. This is in contrast with objective metrics, which instead record a positive impact with HTTP/2 usage. This shows the complexity of understanding the web experience and the need to involve actual users in the quality assessment process.
• [COMMAG-17] Trevisan, Martino and Finamore, Alessandro and Mellia, Marco and Munafo, Maurizio and Rossi, Dario, "Traffic Analysis with Off-the-Shelf Hardware: Challenges and Lessons Learned" In IEEE Communication Magazine, Vol. 55, pp.163 - 169, mar. 2017, DOI 10.1109/MCOM.2017.1600756CM Journal Abstract Bibtex

  @article{DR:COMMAG-17,
    title = {{Traffic Analysis with Off-the-Shelf Hardware: Challenges and Lessons Learned}},
    author = {Trevisan, Martino and Finamore, Alessandro and Mellia, Marco and Munafo, Maurizio and Rossi, Dario},
    month = mar,
    year = {2017},
    journal = {IEEE Communication Magazine},
    volume = {55},
    issue = {3},
    doi = {10.1109/MCOM.2017.1600756CM},
    pages = {163 - 169},
    howpublished = {https://nonsns.github.io/paper/rossi17commag.pdf}
  }
  

  In recent years, the progress in both hardware and software allows user-space applications to capture packets at 10 Gb/s line rate or more, with cheap COTS hardware. However, processing packets at such rates with software is still far from being trivial. In the literature, this challenge has been extensively studied for network intrusion detection systems, where per-packet operations are easy to parallelize with support of hardware acceleration. Conversely, the scalability of statistical traffic analyzers (STAs) is intrinsically complicated by the need to track per-flow state to collect statistics. This challenge has received less attention so far, and it is the focus of this work. We present and discuss design choices to enable a STA to collects hundreds of per-flow metrics at a multi-10-Gb/s line rate. We leverage a handful of hardware advancements proposed over the last years (e.g., RSS queues, NUMA architecture), and we provide insights on the trade-offs they imply when combined with state-of-the-art packet capture libraries and the multi-process paradigm. We outline the principles to design an optimized STA, and we implement them to engineer DPDKStat, a solution combining the Intel DPDK framework with the traffic analyzer Tstat. Using traces collected from real networks, we demonstrate that DPDKStat achieves 40 Gb/s of aggregated rate with a single COTS PC
• [TOMPECS-16] De Cicco, Luca and Gong, Yixi and Rossi, Dario and Leonardi, Emilio, "A control theoretic analysis of low-priority congestion control reprioritization under AQM" In ACM Transactions on Modeling and Performance Evaluation of Computer Systems, Vol. 1, pp.17:1–17:33, sep. 2016, Journal Abstract Bibtex

  @article{DR:TOMPECS-16,
    title = {A control theoretic analysis of low-priority congestion control reprioritization under AQM},
    author = {De Cicco, Luca and Gong, Yixi and Rossi, Dario and Leonardi, Emilio},
    year = {2016},
    month = sep,
    journal = {ACM Transactions on Modeling and Performance Evaluation of Computer Systems},
    volume = {1},
    issue = {4},
    pages = {17:1--17:33},
    topic = {ledbat,ledbat+aqm},
    howpublished = {https://nonsns.github.io/paper/rossi16tompecs.pdf}
  }
  

  Recently, a negative interplay has been shown to arise when scheduling/Active Queue Management (AQM) techniques and low-priority congestion control protocols are used together; namely, AQM resets the relative level of priority among congestion control protocols. This work explores this issue by carrying out a control-theoretic analysis of the dynamical system to prove some fundamental properties that fully characterize the reprioritization phenomenon. In particular, (i) we provide the closed-form solution of the equilibrium in the open loop (i.e., fixing a target loss probability p); (ii) we provide a stability analysis and a characterization of the reprioritization phenomenon when closing the loop with AQM (i.e., that dynamically adjusts the system loss probability). Our results are important as the characterization of the reprioritization phenomenon is not only quantitatively accurate for the specific protocols and AQM considered but also qualitatively accurate for a broader range of congestion control protocol and AQM combinations. Finally, while we find a sufficient condition to avoid the reprioritization phenomenon, we also show, at the same time, such conditions to be likely impractical: Therefore, we propose a simple and practical system-level solution that is able to reinstate priorities among protocols.
• [ITC28b] Tortelli, Michele and Rossi, Dario and Leonardi, Emilio, "ModelGraft: Accurate, Scalable, and Flexible Performance Evaluation of General Cache Networks" ITC28 sep. 2016, Conference Abstract Bibtex

  @inproceedings{DR:ITC28b,
    title = {ModelGraft: Accurate, Scalable, and Flexible Performance Evaluation of General Cache Networks},
    author = {Tortelli, Michele and Rossi, Dario and Leonardi, Emilio},
    year = {2016},
    month = sep,
    booktitle = {ITC28},
    topic = {icn,modeling,scaling},
    howpublished = {https://nonsns.github.io/paper/rossi16itc28-b.pdf}
  }
  

  Large scale deployments of general cache networks, such as Content Delivery Networks or Information Centric Networking architectures, arise new challenges regarding their performance evaluation for network planning. On the one hand, analytical models can hardly represent in details all the interactions of complex replacement, replication, and routing policies on arbitrary topologies. On the other hand, the sheer size of networks and content catalogs makes event-driven simulation techniques inherently non-scalable. We propose a new technique for the performance evaluation of large-scale caching systems that intelligently integrates elements of stochastic analysis within a MonteCarlo simulative approach, that we colloquially refer to as ModelGraft. Our approach (i) leverages the intuition that complex scenarios can be mapped to a simpler equivalent scenario that builds upon Time-To-Live (TTL) caches; it (ii) significantly downscales the scenario to lower computation and memory complexity, while, at the same time, preserving its properties to limit accuracy loss; finally, it (iii) is simple to use and robust, as it autonomously converges to a consistent state through a feedback-loop control system, regardless of the initial state. Performance evaluation shows that, with respect to classic event-driven simulation, ModelGraft gains over two orders of magnitude in both CPU time and memory complexity, while limiting accuracy loss below 2%. In addition, we show that ModelGraft extends performance evaluation well beyond the boundaries of classic approaches, by enabling study of Internet-scale scenarios with content catalogs comprising hundreds of billions objects.
• [ITC28a] Araldo, Andrea and Dan, Gyorgy and Rossi, Dario, "Stochastic Dynamic Cache Partitioning for Encrypted Content Delivery" ITC28, Runner-up for best paper award and receipient of the IEEE ComSoc/ISOC Internet Technical Committee Best paper award 2016-2017 sep. 2016, Conference Award Abstract Bibtex

  @inproceedings{DR:ITC28a,
    title = {Stochastic Dynamic Cache Partitioning for Encrypted Content Delivery},
    author = {Araldo, Andrea and Dan, Gyorgy and Rossi, Dario},
    year = {2016},
    month = sep,
    booktitle = {ITC28, Runner-up for best paper award and receipient of the IEEE ComSoc/ISOC Internet Technical Committee Best paper award 2016-2017},
    topic = {icn,optimization,streaming},
    note = {bestpaperaward},
    howpublished = {https://nonsns.github.io/paper/rossi16itc28-a.pdf}
  }
  

  In-network caching is an appealing solution to cope with the increasing bandwidth demand of video, audio and data transfer over the Internet. Nonetheless, an increasing share of content delivery services adopt encryption through HTTPS, which is not compatible with traditional ISP-managed approaches like transparent and proxy caching. This raises the need for solutions involving both Internet Service Providers (ISP) and Content Providers (CP): by design, the solution should preserve business-critical CP information (e.g., content popularity, user preferences) on the one hand, while allowing for a deeper integration of caches in the ISP architecture (e.g., in 5G femto-cells) on the other hand. In this paper we address this issue by considering a contentoblivious ISP-operated cache. The ISP allocates the cache storage to various content providers so as to maximize the bandwidth savings provided by the cache: the main novelty lies in the fact that, to protect business-critical information, ISPs only need to measure the aggregated miss rates of the individual CPs and does not need to be aware of the objects that are requested, as in classic caching. We propose a cache allocation algorithm based on a perturbed stochastic subgradient method, and prove that the algorithm converges close to the allocation that maximizes the overall cache hit rate. We use extensive simulations to validate the algorithm and to assess its convergence rate under stationary and non-stationary content popularity. Our results (i) testify the feasibility of content-oblivious caches and (ii) show that the proposed algorithm can achieve within 10% from the global optimum in our evaluation.
• [SIGCOMM-QoE-16] Bocchi, Enrico and De Cicco, Luca and Rossi, Dario, "Measuring the Quality of Experience of Web users" ACM SIGCOMM Workshop on QoE-based Analysis and Management of Data Communication Networks (Internet-QoE 2016), selected as best paper in the workshop for reprint in ACM SIGCOMM Comput. Commun. Rev. aug. 2016, Conference Award Bibtex

  @inproceedings{DR:SIGCOMM-QoE-16,
    title = {Measuring the Quality of Experience of Web users},
    author = {Bocchi, Enrico and De Cicco, Luca and Rossi, Dario},
    year = {2016},
    month = aug,
    booktitle = {ACM SIGCOMM Workshop on QoE-based Analysis and Management of Data Communication Networks (Internet-QoE 2016), selected as best paper in the workshop for reprint in ACM SIGCOMM Comput. Commun. Rev.},
    topic = {internetmeasurement,qoe},
    note = {bestpaperaward},
    howpublished = {https://nonsns.github.io/paper/rossi16internet-qoe.pdf}
  }
  

FP7 mPlane 34

• [JSAC-16] Cicalese, Danilo and Joumblatt, Diana and Rossi, Dario and Buob, Marc-Olivier and Auge, Jordan and Friedman, Timur, "Latency-Based Anycast Geolocalization: Algorithms, Software and Datasets" In IEEE Journal on Selected Areas of Communications, Special issue on Measuring and Troubleshooting the Internet, Vol. 6, pp.1889–1903, jun. 2016, Journal Abstract Bibtex

  @article{DR:JSAC-16,
    title = {Latency-Based Anycast Geolocalization: Algorithms, Software and Datasets},
    author = {Cicalese, Danilo and Joumblatt, Diana and Rossi, Dario and Buob, Marc-Olivier and Auge, Jordan and Friedman, Timur},
    year = {2016},
    month = jun,
    journal = {IEEE Journal on Selected Areas of Communications, Special issue on Measuring and Troubleshooting the Internet},
    issue = {34},
    volume = {6},
    pages = {1889--1903},
    topic = {internetmeasurement,ancast},
    howpublished = {https://nonsns.github.io/paper/rossi16jsac.pdf}
  }
  

  Use of IP-layer anycast has increased in the last few years beyond the DNS realm. Yet, existing measurement techniques to identify and enumerate anycast replicas exploit specifics of the DNS protocol, which limits their applicability to this particular service. With this paper, we not only propose and thoroughly validate a protocol-agnostic technique for anycast replicas discovery and geolocation, but also provide the community with open source software and datasets to replicate our experimental results, as well as facilitating the development of new techniques such as ours. In particular, our proposed method achieves thorough enumer-ation and city-level geolocalization of anycast instances from a set of known vantage points. The algorithm features an iterative workflow, pipelining enumeration (an optimization problem using latency as input) and geolocalization (a classification problem using side channel information such as city population) of anycast replicas. Results of a thorough validation campaign show our algorithm to be robust to measurement noise, and very lightweight as it requires only a handful of latency measurements.
• [COMNET-16a] Espinet, Francois and Joumblatt, Diana and Rossi, Dario, "Framework, Models and Controlled Experiments of Network Troubleshooting" In Elsevier Computer Networks, Vol. 107, pp.36-54, jun. 2016, Journal Abstract Bibtex

  @article{DR:COMNET-16a,
    title = {Framework, Models and Controlled Experiments of Network Troubleshooting},
    author = {Espinet, Francois and Joumblatt, Diana and Rossi, Dario},
    year = {2016},
    pages = {36-54},
    month = jun,
    volume = {107},
    journal = {Elsevier Computer Networks},
    topic = {troubleshooting},
    howpublished = {https://nonsns.github.io/paper/rossi16comnet-a.pdf}
  }
  

  Growing network complexity mandates automated tools and methodologies for troubleshooting. In this paper, we follow a crowd-sourcing trend and argue for the need to deploy measurement probes at the edge of the network, which can be either under the control of the users (e.g., end-user devices) or the ISP (e.g., home gateways), and that raises an interesting tradeoff. Our first contribution consists in the definition of a framework for network troubleshooting, and its implementation as open source software named NetProbes. In data mining terms, depending on the amount of information available to the probes (e.g., ISP topology), we formalize the network troubleshooting task as either a clustering or a classification problem. In networking terms, these algorithms allow respectively end-users to assess the severity of the network performance degradation, and ISPs to precisely identify the faulty link. We solve both problems with an algorithm that achieves perfect classification under the assumption of a strategic selection of probes (e.g., assisted by an ISP), and assess its performance degradation under a naive random selection. Our algorithm is generic, as it is agnostic to the network performance metrics; scalable, as it requires firing only few measurement events and simple processing; flexible, as clustering and classification stages are pipelined, so that the execution naturally adapts to the information available at the vantage point where the probe is deployed; and reliable, as it produces results that match the expectations of simple analytical models. Our second contribution consists in a careful evaluation of the framework. Previous work on network troubleshooting has so far tackled the problem with either more theoretical or more practical approaches: inherently, evaluation methodologies lack either realism or control. In this paper, we counter this problem by conducting controlled experiments with a rigorous and reproducible methodology that contrasts expectations yielded by analytical models to the experimental results gathered running our NetProbes software in the Mininet emulator. As integral part of our methodology, we perform a thorough calibration of the measurement tools employed by NetProbes to measure two example metrics of interest, namely delay and bandwidth: we show this step to be crucial, as otherwise significant biases in the measurements techniques could lead to wrong assessment of algorithmic performance. Albeit our NetProbes software is far from being a carrier-grade solution for network troubleshooting (since it does not consider neither multiple contemporary measurements, nor multiple failures, and given that we experiment with a limited number of metrics), our controlled study allows making several interesting observation that help designing such an automated troubleshooting system.
• [TMA-16] Giordano, Danilo and Cicalese, Danilo and Finamore, Alessandro and Mellia, Marco and Munafo, Maurizio and Joumblatt, Diana and Rossi, Dario, "A First Characterization of Anycast Traffic from Passive Traces" IFIP workshop on Traffic Monitoring and Analysis (TMA), apr. 2016, Conference Abstract Bibtex

  @inproceedings{DR:TMA-16,
    title = {A First Characterization of Anycast Traffic from Passive Traces},
    author = {Giordano, Danilo and Cicalese, Danilo and Finamore, Alessandro and Mellia, Marco and Munafo, Maurizio and Joumblatt, Diana and Rossi, Dario},
    year = {2016},
    month = apr,
    booktitle = {IFIP workshop on Traffic Monitoring and Analysis (TMA),},
    pages = {30-38},
    topic = {anycast,internetmeasurement,passivemeasurement},
    howpublished = {https://nonsns.github.io/paper/rossi16tma.pdf}
  }
  

  IP anycast routes packets to the topologically nearest server according to BGP proximity. In the last years, new players have started adopting this technology to serve web content via Anycast-enabled CDNs (A-CDN). To the best of our knowledge, in the literature, there are studies that focus on a specific A-CDN deployment, but little is known about the users and the services that A-CDNs are serving in the Internet at large. This prompted us to perform a passive characterization study, bringing out the principal A-CDN actors in our monitored setup, the services they offer, their penetration, etc. Results show a very heterogeneous picture, with A-CDN empowered services that are very popular (e.g., Twitter or Bing), serve a lot of different contents (e.g., Wordpress or adult content), and even include audio/video streaming (e.g., Soundcloud, or Vine). Our measurements show that the A-CDN technology is quite mature and popular, with more than 50% of web users that access content served by a A-CDN during peak time.
• [SIMPAT-16] Tortelli, Michele and Rossi, Dario and Boggia, Gennaro and Grieco, Luigi Alfredo, "ICN software tools: survey and cross-comparison" In Elsevier Simulation Modelling Practice and Theory, Vol. 63, pp.23–46, apr. 2016, Journal Abstract Bibtex

  @article{DR:SIMPAT-16,
    title = {ICN software tools: survey and cross-comparison},
    author = {Tortelli, Michele and Rossi, Dario and Boggia, Gennaro and Grieco, Luigi Alfredo},
    year = {2016},
    journal = {Elsevier Simulation Modelling Practice and Theory},
    volume = {63},
    month = apr,
    pages = {23--46},
    topic = {icn,ccnsim},
    howpublished = {https://nonsns.github.io/paper/rossi16simpat.pdf}
  }
  

  Research interest on Information Centric Networking (ICN) has been sharply growing. Although new architectures, algorithms, and analytical models have been proposed, their evaluation remains often isolated and not rigorously verified by the research community. This paper initially portrays the composition of open source software tools available for ICN, certifying the predominance of Content Centric Networking (CCN)/Named Data Networking (NDN) simulators. Then, inspired by similar works related to the P2P field, it surveys related research papers to qualify the ICN literature produced so far, finding that a large fraction of contributions either uses custom, proprietary, and unavailable software, or even plainly fails to mention any information in this regard. By adopting a rigorous methodology, in the second part of the paper four simulators, namely ndnSIM, ccnSim, CCNPL-Sim, and Icarus, are cross-compared under several key aspects. Our findings confirm both their accuracy with respect to reference theoretical models in simple settings, and their consistency in more complex scenario. Additionally, our analysis can both assist researchers in the choice of the tool that best fits their needs, and provide guidelines to avoid common pitfalls in the ICN performance evaluation.
• [DPDKStat-16] Trevisan, Martino and Finamore, Alessandro and Mellia, Marco and Munafo, Maurizio and Rossi, Dario, "DPDKStat: 40Gbps Statistical Traffic Analysis with Off-the-Shelf Hardware" Tech. Rep. 2016, Conference Bibtex

  @inproceedings{DR:DPDKStat-16,
    title = {DPDKStat: 40Gbps Statistical Traffic Analysis with Off-the-Shelf Hardware},
    author = {Trevisan, Martino and Finamore, Alessandro and Mellia, Marco and Munafo, Maurizio and Rossi, Dario},
    year = {2016},
    booktitle = {Tech. Rep.},
    topic = {passivemeasurement,system},
    howpublished = {https://nonsns.github.io/paper/DPDKStat-techrep.pdf}
  }
  
• [TECHREP-16] Cicalese, Danilo and Joumblatt, Diana and Rossi, Dario and Buob, Marc-Olivier and Auge, Jordan and Friedman, Timur, "Latency-Based Anycast Geolocalization: Algorithms, Software and Datasets (Extended Technical Report)" Tech. Rep. 2016, Conference Bibtex

  @inproceedings{DR:TECHREP-16,
    title = {Latency-Based Anycast Geolocalization: Algorithms, Software and Datasets (Extended Technical Report)},
    author = {Cicalese, Danilo and Joumblatt, Diana and Rossi, Dario and Buob, Marc-Olivier and Auge, Jordan and Friedman, Timur},
    year = {2016},
    booktitle = {Tech. Rep.},
    topic = {anycast,internetmeasurement},
    howpublished = {https://nonsns.github.io/dataset/anycast/anycast-techrep.pdf}
  }
  
• [CoNEXT-15] Cicalese, Danilo and Auge, Jordan and Joumblatt, Diana and Friedman, Timur and Rossi, Dario, "Characterizing IPv4 Anycast Adoption and Deployment" ACM CoNEXT, awarded the IRTF Applied Network Research Prize at IETF96 dec. 2015, Conference Award Abstract Bibtex

  @inproceedings{DR:CoNEXT-15,
    title = {Characterizing IPv4 Anycast Adoption and Deployment},
    author = {Cicalese, Danilo and Auge, Jordan and Joumblatt, Diana and Friedman, Timur and Rossi, Dario},
    booktitle = {ACM CoNEXT, awarded the IRTF Applied Network Research Prize at IETF96},
    address = {Heidelberg},
    month = dec,
    year = {2015},
    topic = {anycast,internetmeasurement},
    note = {bestpaperaward},
    howpublished = {https://nonsns.github.io/paper/rossi15conext.pdf}
  }
  

  This paper provides a comprehensive picture of IP-layer anycast adoption in the current Internet. We carry on multiple IPv4 anycast censuses, relying on latency measurement from PlanetLab. Next, we leverage our novel technique for anycast detection, enumeration, and geolocation to quantify anycast adoption in the Internet. Our technique is scalable and, unlike previous efforts that are bound to exploiting DNS, is protocol-agnostic. Our results show that major Internet companies (including tier-1 ISPs, over-the-top operators, Cloud providers and equipment vendors) use anycast: we find that a broad range of TCP services are offered over anycast, the most popular of which include HTTP and HTTPS by anycast CDNs that serve websites from the top-100k Alexa list. Additionally, we complement our characterization of IPv4 anycast with a description of the challenges we faced to collect and analyze large-scale delay measurements, and the lessons learned.
• [TRAC-15] Bocchi, Enrico and Safari, Ali and Traverso, Stefano and Finamore, Alessandro and Di Gennaro, Valeria and Mellia, Marco and Munafo, Maurizio and Rossi, Dario, "Impact of Carrier-Grade NAT on Web Browsing" 6th International Workshop on TRaffic Analysis and Characterization (TRAC), Best paper award aug. 2015, Conference Award Abstract Bibtex

  @inproceedings{DR:TRAC-15,
    title = {Impact of Carrier-Grade NAT on Web Browsing},
    author = {Bocchi, Enrico and Safari, Ali and Traverso, Stefano and Finamore, Alessandro and Di Gennaro, Valeria and Mellia, Marco and Munafo, Maurizio and Rossi, Dario},
    year = {2015},
    booktitle = {6th International Workshop on TRaffic Analysis and Characterization (TRAC), Best paper award},
    month = aug,
    topic = {internetmeasurement,passivemeasurement},
    note = {bestpaperaward},
    howpublished = {https://nonsns.github.io/paper/rossi15trac.pdf}
  }
  

  Public IPv4 addresses are a scarce resource. While IPv6 adoption is lagging, Network Address Translation (NAT) technologies have been deployed over the last years to alleviate IPv4 exiguity and their high rental cost. In particular, Carrier- Grade NAT (CGN) is a well known solution to mask a whole ISP network behind a limited amount of public IP addresses, significantly reducing expenses. Despite its economical benefits, CGN can introduce connectivity issues which have sprouted a considerable effort in research, development and standardization. However, to the best of our knowledge, little effort has been dedicated to investigate the impact that CGN deployment may have on users traffic. This paper fills the gap. We leverage passive measurements from an ISP network deploying CGN and, by means of the Jensen- Shannon divergence, we contrast several performance metrics considering customers being offered public or private addresses. In particular, we gauge the impact of CGN presence on users web browsing experience. Our results testify that CGN is a mature and stable technology as, if properly deployed, it does not harm users web browsing experience. Indeed, while our analysis lets emerge expected stochastic differences of certain indexes (e.g., the difference in the path hop count), the measurements related to the quality of users browsing are otherwise unperturbed. Interestingly, we also observe that CGN
• [EuCNC-15] Rossi, D. et al., "The mPlane distributed measurement infrastructure and its reference implementation" Exhibition at EuCNC’15 jun. 2015, Conference Bibtex

  @inproceedings{DR:EuCNC-15,
    author = {Rossi, D. et al.},
    title = {The mPlane distributed measurement infrastructure and its reference implementation},
    booktitle = {Exhibition at EuCNC'15},
    year = {2015},
    month = jun,
    topic = {internetmeasurement},
    howpublished = {http://www.ict-mplane.eu/blogs/mplane-european-conference-networks-and-communications-eucnc-2015}
  }
  
• [INFOCOM-15b] Cicalese, Danilo and Joumblatt, Diana and Rossi, Dario and Buob, Marc-Olivier and Auge, Jordan and Friedman, Timur, "A Lightweight Anycast Enumeration and Geolocation" IEEE INFOCOM, Demo Session apr. 2015, Conference Abstract Bibtex

  @inproceedings{DR:INFOCOM-15b,
    title = {A Lightweight Anycast Enumeration and Geolocation},
    author = {Cicalese, Danilo and Joumblatt, Diana and Rossi, Dario and Buob, Marc-Olivier and Auge, Jordan and Friedman, Timur},
    year = {2015},
    booktitle = {IEEE INFOCOM, Demo Session},
    month = apr,
    address = {Hong Kong, China},
    topic = {anycast,internetmeasurement},
    howpublished = {https://nonsns.github.io/paper/rossi15infocom-b.pdf}
  }
  

  Several Internet services such as CDNs, DNS name servers, and sinkholes use IP-layer anycast to reduce user response times and increase robustness with respect to network failures and denial of service attacks. However, current geolocation tools fail with anycast IP addresses. In our recent work, we remedy to this by developing an anycast detection, enumeration, and geolocation technique based on a set of delay measurements from a handful of geographically distributed vantage points. The technique (i) detects if an IP is anycast, (ii) enumerates replicas by finding the maximum set of non-overlapping disks (i.e., areas centered around vantage points), and (iii) geolocates the replicas by solving a classification problem and assigning the server location to the most likely city. We propose to demo this technique. In particular, we visually show how to detect an anycast IP, enumerate its replicas, and geolocate them on a map. The demo allows to browse previously geolocated services, as well as to explore new targets on demand.
• [INFOCOM-15a] Cicalese, Danilo and Joumblatt, Diana and Rossi, Dario and Buob, Marc-Olivier and Auge, Jordan and Freeman, Timur, "A Fistful of Pings: Accurate and Lightweight Anycast Enumeration and Geolocation" IEEE INFOCOM apr. 2015, Conference Abstract Bibtex

  @inproceedings{DR:INFOCOM-15a,
    title = {A Fistful of Pings: Accurate and Lightweight Anycast Enumeration and Geolocation},
    author = {Cicalese, Danilo and Joumblatt, Diana and Rossi, Dario and Buob, Marc-Olivier and Auge, Jordan and Freeman, Timur},
    year = {2015},
    booktitle = {IEEE INFOCOM},
    month = apr,
    address = {Hong Kong, China},
    topic = {anycast,internetmeasurement},
    howpublished = {https://nonsns.github.io/paper/rossi15infocom.pdf}
  }
  

  Use of IP-layer anycast has increased in the last few years: once relegated to DNS root and top-level domain servers, anycast is now commonly used to assist distribution of general purpose content by CDN providers. Yet, the measurement techniques for discovering anycast replicas have been designed around DNS, limiting their usefulness to this particular service. This raises the need for protocol agnostic methodologies, that should additionally be as lightweight as possible in order to scale up anycast service discovery. This is precisely the aim of this paper, which proposes a new method for exhaustive and accurate enumeration and city-level geolocation of anycast instances, requiring only a handful of latency measurements from a set of known vantage points. Our method exploits an iterative workflow that enumerates (an optimization problem) and geolocates (a classification problem) anycast replicas. We thoroughly validate our methodology on available ground truth (several DNS root servers), using multiple measurement infrastructures (PlanetLab, RIPE), obtaining extremely accurate results (even with simple algorithms, that we compare with the global optimum), that we make available to the scientific community. Compared to the state of the art work that appeared in INFOCOM 2013 and IMC 2013, our technique (i) is not bound to a specific protocol, (ii) requires 1000 times fewer vantage points, not only (iii) achieves over 50% recall but also (iv) accurately identifies the city-level geolocation for over 78% of the enumerated servers, with (v) a mean geolocation error of 361 km for all enumerated servers.
• [AIMS-15] Cicalese, Danilo and Auge, Jordan and Joumblatt, Diana and Rossi, Dario and Friedman, Timur, "Anycast census and geolocation" 7th Workshop on Active Internet Measurements (AIMS 2015) mar. 2015, Conference Bibtex

  @inproceedings{DR:AIMS-15,
    title = {Anycast census and geolocation},
    author = {Cicalese, Danilo and Auge, Jordan and Joumblatt, Diana and Rossi, Dario and Friedman, Timur},
    year = {2015},
    booktitle = {7th Workshop on Active Internet Measurements (AIMS 2015)},
    month = mar,
    address = {San Diego, CA},
    topic = {anycast,internetmeasurement},
    howpublished = {https://nonsns.github.io/paper/rossi15aims.pdf}
  }
  
• [ICN-14c] Imbrenda, Claudio and Muscariello, Luca and Rossi, Dario, "Analyzing Cacheable Traffic in ISP Access Networks for Micro CDN applications via Content-Centric Networking" 1st ACM SIGCOMM Conference on Information-Centric Networking (ICN-2014) sep. 2014, Conference Abstract Bibtex

  @inproceedings{DR:ICN-14c,
    title = {Analyzing Cacheable Traffic in ISP Access Networks for Micro CDN applications via Content-Centric Networking},
    author = {Imbrenda, Claudio and Muscariello, Luca and Rossi, Dario},
    booktitle = {1st ACM SIGCOMM Conference on Information-Centric Networking (ICN-2014)},
    address = {Paris, France},
    month = sep,
    year = {2014},
    pages = {57-66},
    howpublished = {https://nonsns.github.io/paper/rossi14icn-c.pdf}
  }
  

  Web content coming from outside the ISP is today skyrocketing, causing significant additional infrastructure costs to network operators. The reduced marginal revenues left to ISPs, whose business is almost entirely based on declining flat rate subscriptions, call for significant innovation within the network infrastructure, to support new service delivery. In this paper, we suggest the use of micro CDNs in ISP access and back-haul networks to reduce redundant web traffic within the ISP infrastructure while improving user’s QoS. With micro CDN we refer to a content delivery system composed of (i) a high speed caching substrate, (ii) a content based routing protocol and (iii) a set of data transfer mechanisms made available by content-centric networking. The contribution of this paper is twofold. First, we extensively analyze more than one month of web traffic via continuous monitoring between the access and back-haul network of Orange in France. Second, we characterize key properties of monitored traffic, such as content popularity and request cacheability, to infer potential traffic reduction enabled by the introduction of micro CDNs. Based on these findings, we then perform micro CDN dimensioning in terms of memory requirements and provide guidelines on design choices
• [TRAC-14] Araldo, Andrea and Rossi, Dario, "A per-Application Account of Bufferbloat: Causes and Impact on Users" 5th International Workshop on TRaffic Analysis and Characterization (TRAC), Best paper award aug. 2014, Conference Award Abstract Bibtex

  @inproceedings{DR:TRAC-14,
    title = {A per-Application Account of Bufferbloat: Causes and Impact on Users},
    author = {Araldo, Andrea and Rossi, Dario},
    booktitle = {5th International Workshop on TRaffic Analysis and Characterization (TRAC), Best paper award},
    year = {2014},
    address = {Nicosia, Cyprus},
    month = aug,
    note = {bestpaperaward},
    howpublished = {https://nonsns.github.io/paper/rossi14trac.pdf}
  }
  

  We propose a methodology to gauge the extent of queueing delay (aka bufferbloat) in the Internet, based on purely passive measurement of TCP traffic. We implement our methodology in Tstat and make it available as open source software. We leverage Deep Packet Inspection (DPI) and behavioral classification of Tstat to breakdown the queueing delay across different applications, in order to evaluate the impact of bufferbloat on user experience. We show that there is no correlation between the ISP traffic load and the queueing delay, thus confirming that bufferbloat is related only to the traffic of each single user (or household). Finally, we use frequent itemset mining techniques to associate the amount of queueing delay seen by each host with the set of its active applications, with the goal of investigating the root cause of bufferbloat.
• [COMMAG-14] Trammell, Brian and Casas, Pedro and Rossi, Dario and Bar, Arian and Ben-Houidi, Zied and Leontiadis, Ilias and Szemethy, Tivadar and Mellia, Marco, "mPlane: an Intelligent Measurement Plane for the Internet" In IEEE Communications Magazine, Special Issue on Monitoring and Troubleshooting Multi-domain Networks using Measurement Federations, pp.148-156, may. 2014, Journal Abstract Bibtex

  @article{DR:COMMAG-14,
    author = {Trammell, Brian and Casas, Pedro and Rossi, Dario and Bar, Arian and Ben-Houidi, Zied and Leontiadis, Ilias and Szemethy, Tivadar and Mellia, Marco},
    title = {mPlane: an Intelligent Measurement Plane for the Internet},
    journal = {IEEE Communications Magazine, Special Issue on Monitoring and Troubleshooting Multi-domain Networks using Measurement Federations},
    vol = {42},
    pages = {148-156},
    issue = {5},
    month = may,
    year = {2014},
    howpublished = {https://nonsns.github.io/paper/rossi14commag.pdf}
  }
  

  The Internet universality is based on its decentralization and diversity. However, its distributed nature leads to operational brittleness and difficulty in identifying the root causes of performance and availability issues, especially when the involved systems span multiple administrative domains. The first step to address this fragmentation is coordinated measurement: we propose to complement the current Internet data and control planes with a measurement plane, or mPlane for short. mPlane distributed measurement infrastructure collects and analyzes traffic measurements at a wide variety of scales to monitor the network status. Its architecture is centered on a flexible control interface, allowing the incorporation of existing measurement tools through lightweight mPlane proxy components, and offering dynamic support for new capabilities. A focus on automated, iterative measurement makes the platform well-suited to troubleshooting support. This is supported by a reasoning system, which applies machine learning algorithms to learn from success and failure in drilling down to the root cause of a problem. This article describes the mPlane architecture and shows its applicability to several distributed measurement problems involving content delivery networks and Internet service roviders. A first case study presents the tracking and iterative analysis of cache selection policies in Akamai, while a second example focuses on the cooperation between Internet service providers and content delivery networks to better orchestrate their traffic engineering decisions and jointly improve their performance.
• [TMA-14a] Colabrese, S. and Rossi, D. and Mellia, M., "Aggregation of statistical data from passive probes: Techniques and best practices" Traffic Measurement and Analysis (TMA) apr. 2014, Conference Abstract Bibtex

  @inproceedings{DR:TMA-14a,
    title = {Aggregation of statistical data from passive probes: Techniques and best practices},
    author = {Colabrese, S. and Rossi, D. and Mellia, M.},
    year = {2014},
    address = {London, UK},
    pages = {38-50},
    booktitle = {Traffic Measurement and Analysis (TMA)},
    month = apr,
    howpublished = {https://nonsns.github.io/paper/rossi14tma-a.pdf}
  }
  

  Passive probes continuously generate statistics on large number of metrics, that are possibly represented as probability mass functions (pmf). The need for consolidation of several pmfs arises in two contexts, namely: (i) whenever a central point collects and aggregates measurement of multiple disjoint vantage points, and (ii) whenever a local measurement processed at a single vantage point needs to be distributed over multiple cores of the same physical probe, in order to cope with growing link capacity. In this work, we take an experimental approach and study both cases using, whenever possible, open source software and datasets. Considering different consolidation strategies, we assess their accuracy in estimating pmf deciles (from the 10th to the 90th) of diverse metrics, obtaining general design and tuning guidelines. In our dataset, we find that Monotonic Spline Interpolation over a larger set of percentiles (e.g., adding 5th, 10th, 15th, and so on) allow fairly accurate pmf consolidation in both the multiple vantage points (median error is about 1%, maximum 30%) and local processes (median 0.1%, maximum 1%) cases.
• [TMA-14c] Rossi, Dario and Pujol, Guilhem and Wang, Xiao and Mathieu, Fabien, "Peeking Through the BitTorrent Seedbox Hosting Ecosystem" Traffic Measurement and Analysis (TMA) apr. 2014, Conference Abstract Bibtex

  @inproceedings{DR:TMA-14c,
    title = {Peeking Through the BitTorrent Seedbox Hosting Ecosystem},
    author = {Rossi, Dario and Pujol, Guilhem and Wang, Xiao and Mathieu, Fabien},
    year = {2014},
    booktitle = {Traffic Measurement and Analysis (TMA)},
    month = apr,
    howpublished = {https://nonsns.github.io/paper/rossi14tma-c.pdf}
  }
  

  In this paper, we propose a lightweight method for detecting and classifying BitTorrent content providers with a minimal amount of resources. While heavy methodologies are typically used (which require long term observation and data exchange with peers of the swarm and/or a semantic analysis of torrent websites), we instead argue that such complexity can be avoided by analyzing the correlations between peers and torrents. We apply our methodology to study over 50K torrents injected in ThePirateBay during one month, collecting more than 400K IPs addresses. Shortly, we find that exploiting the correlations not only enhances the classification accuracy keeping the technique lightweight (our methodology reliably identifies about 150 seedboxes), but also uncovers seeding behaviors that were not previously noticed (e.g., as multi-port and multi-host seeding). Finally, we correlate the popularity of seedbox hosting in our dataset to criteria (e.g., cost, storage space, Web popularity) that can bias the selection process of BitTorrent content providers.
• [TMA-14b] Nassopulos, Georges and Rossi, Dario and Gringoli, Francesco and Nava, Lorenzo and Dusi, Maurizio and del Rio, Pedro Maria Santiago, "Flow management at multi-Gbps: tradeoffs and lessons learned" Traffic Measurement and Analysis (TMA) apr. 2014, Conference Abstract Bibtex

  @inproceedings{DR:TMA-14b,
    title = {Flow management at multi-Gbps: tradeoffs and lessons learned},
    author = {Nassopulos, Georges and Rossi, Dario and Gringoli, Francesco and Nava, Lorenzo and Dusi, Maurizio and del Rio, Pedro Maria Santiago},
    year = {2014},
    booktitle = {Traffic Measurement and Analysis (TMA)},
    month = apr,
    pages = {1-14},
    howpublished = {https://nonsns.github.io/paper/rossi14tma-b.pdf}
  }
  

  While the ultimate goal of kernel-level network stacks is to manage individual packets at line rate, the goal of user-level network monitoring applications is instead to match packets with the flow they belong to, and take actions accordingly. With current improvements in Network Interface Cards hardware and network software stacks, traffic monitors and traffic analyzers are fed with multi-Gbps streams of packets – which de facto pushes bottlenecks from kernel-level networking stack up to user-level applications. In this paper, we argue that flow management is a crucial module for any user-application that needs to process traffic at multiple Gbps, and we study the performance impact of different design choices of the flow management module by adopting a trace-driven emulation approach. While our results do not show a single “best” system settings under all circumstances, they highlight several tradeoffs, in terms of, e.g., the kind of structure, its size, and the computational complexity, that may affect system performance in a non-trivial way. We further make our software tools available to the scientific community to promote sharing of best practices
• [PAM-14c] Mazloum, R. and Buob, M.-O. and Auge, J. and Baynat, B. and Friedman, T. and Rossi, D., "Violation of Interdomain Routing Assumptions" Passive and Active Measurement (PAM), mar. 2014, Conference Abstract Bibtex

  @inproceedings{DR:PAM-14c,
    author = {Mazloum, R. and Buob, M.-O. and Auge, J. and Baynat, B. and Friedman, T. and Rossi, D.},
    title = {Violation of Interdomain Routing Assumptions},
    booktitle = {Passive and Active Measurement (PAM),},
    year = {2014},
    address = {Los Angeles, USA},
    month = mar,
    howpublished = {https://nonsns.github.io/paper/rossi14pam-c.pdf}
  }
  
• [PAM-14b] Casoria, P. and Rossi, D. and Auge, J. and Buob, Marc-Olivier and Friedman, T. and Pescape, A., "Distributed active measurement of Internet queuing delays" Passive and Active Measurement (PAM), Extended Abstract mar. 2014, Conference Abstract Bibtex

  @inproceedings{DR:PAM-14b,
    author = {Casoria, P. and Rossi, D. and Auge, J. and Buob, Marc-Olivier and Friedman, T. and Pescape, A.},
    title = {Distributed active measurement of Internet queuing delays},
    booktitle = {Passive and Active Measurement (PAM), Extended Abstract},
    year = {2014},
    address = {Los Angeles, USA},
    month = mar,
    howpublished = {https://nonsns.github.io/paper/rossi14pam-b.pdf}
  }
  

  Despite growing link capacities, over-dimensioned buffers are still causing, in the Internet of the second decade of the third millenium, hosts to suffer from severe queuing delays (or bufferbloat). While maximum bufferbloat possibly exceeds few seconds, it is far less clear how often this maximum is hit in practice. This paper reports on our ongoing work to build a spatial and temporal map of Internet bufferbloat, describing a system based on distributed agents running on PlanetLab that aims at providing a quantitative answer to the above question.
• [COMNET-14a] Testa, Claudio and Rossi, Dario, "Delay-based congestion control: Flow vs. BitTorrent swarm perspectives" In Computer Networks, Vol. 60, No. 0, pp.115 – 128, feb. 2014, Journal Abstract Bibtex

  @article{DR:COMNET-14a,
    title = {Delay-based congestion control: Flow vs. BitTorrent swarm perspectives},
    author = {Testa, Claudio and Rossi, Dario},
    month = feb,
    journal = {Computer Networks},
    volume = {60},
    number = {0},
    pages = {115 -- 128},
    year = {2014},
    issn = {1389-1286},
    howpublished = {https://nonsns.github.io/paper/rossi14comnet-a.pdf}
  }
  

  BitTorrent, one of the most widespread file-sharing P2P applications, recently introduced LEDBAT, a novel congestion control protocol aiming at (i) limiting the additional delay due to queuing, to reduce interference with the rest of user traffic (e.g., Web, VoIP and gaming) sharing the same access bottleneck, and (ii) efficiently using the available link capacity, to provide users with good BitTorrent performance at the same time. In this work, we adopt two complementary perspectives: namely, a flow viewpoint to assess the Quality of Service (QoS) as in classic congestion control studies, and a BitTorrent swarm viewpoint to assess peer-to-peer users Quality of Experience (QoE). We additionally point out that congestion control literature is rich of protocols, such as VEGAS, LP, and NICE sharing similarities with LEDBAT, that is therefore mandatory to consider in the analysis. Hence, adopting the above viewpoints we both (i) contrast LEDBAT to the other protocols and (ii) provide deep understanding of the novel protocol and its implication on QoS and QoE. Our simulation based investigation yields several insights. At flow-level, we gather LEDBAT to be lowest priority among all protocols, which follows from its design that strives to explicitly bound the queuing delay at the bottleneck link to a maximum target value. At the same time, we see that this very same protocol parameter can be exploited by adversaries, that can set a higher target to gain an unfair advantage over competitors. Interestingly, swarm-level performance exhibit an opposite trade-off, with smaller targets being more advantageous for QoE of BitTorrent users. This can be explained with the fact that larger delay targets slow down BitTorrent signaling task, with possibly negative effect on the swarming protocol efficiency. Additionally, we see that for the above reason, in heterogeneous swarms, any delay-based protocol (i.e., not only LEDBAT but also VEGAS or NICE) can yield a competitive QoE advantage over loss-based TCP. Overall this tension between swarm and flow-levels suggests that, at least in current ADSL/cable access bottleneck scenarios, a safe LEDBAT operational point may be used in practice. At the same time, our results also point out that benefits similar to LEDBAT can also be gathered with other delay-based protocols such as VEGAS or NICE.
• [COMNET-14b] Gong, YiXi and Rossi, Dario and Testa, Claudio and Valenti, Silvio and Taht, Dave, "Fighting the bufferbloat: on the coexistence of AQM and low priority congestion control (extended version)" In Computer Networks, Vol. 65, No. 0, pp.255 – 267, 2014, Journal Abstract Bibtex

  @article{DR:COMNET-14b,
    author = {Gong, YiXi and Rossi, Dario and Testa, Claudio and Valenti, Silvio and Taht, Dave},
    title = {{Fighting the bufferbloat: on the coexistence of AQM and low priority congestion control (extended version)}},
    journal = {Computer Networks},
    volume = {65},
    number = {0},
    pages = {255 -- 267},
    year = {2014},
    issn = {1389-1286},
    howpublished = {https://nonsns.github.io/paper/rossi14comnet-b.pdf}
  }
  

  Nowadays, due to excessive queuing, delays on the Internet can grow longer than the round trip time between the Moon and the Earth – for which the “bufferbloa t” term was recently coined. Some point to active queue management (AQM) as the solution. Others propose end-to-end low-priority congestion control techniques (LPCC). Under both approaches, promising advances have been made in recent times: notable examples are CoDel for AQM, and LEDBAT for LPCC. In this paper, we warn of a potentially fateful interaction when AQM and LPCC techniques are combined: namely, AQM resets the relative level of priority between best-effort and low-priority congestion control protocols. We validate the generality of our findings by an extended set of experiments with packet-level ns2 simulation, considering 5 AQM techniques and 3 LPCC protocols, and carry on a thorough sensitivity analysis varying several parameters of the networking scenario. We complete the simulation via an experimental campaign conducted on both controlled testbeds and on the Internet, confirming the reprioritization issue to hold in the real world at least under all combination of AQM policies and LPCC protocols available in the Linux kernel. To promote cross-comparison, we make our scripts and dataset available to the research community.
• [GLOBECOM-13] Chirichella, C. and Rossi, D. and Testa, C. and Friedman, T. and Pescape, A., "Passive bufferbloat measurement exploiting transport layer information" IEEE GLOBECOM dec. 2013, Conference Bibtex

  @inproceedings{DR:GLOBECOM-13,
    title = {Passive bufferbloat measurement exploiting transport layer information},
    author = {Chirichella, C. and Rossi, D. and Testa, C. and Friedman, T. and Pescape, A.},
    year = {2013},
    booktitle = {IEEE GLOBECOM},
    month = dec,
    howpublished = {https://nonsns.github.io/paper/rossi13globecom.pdf}
  }
  
• [CONEXT-13] A. Araldo, D. Rossi, "Dissecting Bufferbloat: Measurement and Per-Application Breakdown of Queueing Delay" ACM CoNEXT’13, Student Workshop dec. 2013, Conference Abstract Bibtex

  @inproceedings{DR:CONEXT-13,
    title = {Dissecting Bufferbloat: Measurement and Per-Application Breakdown of Queueing Delay},
    author = {A. Araldo, D. Rossi},
    year = {2013},
    booktitle = {ACM CoNEXT'13, Student Workshop},
    month = dec,
    pages = {25-26},
    howpublished = {https://nonsns.github.io/paper/rossi13conext.pdf}
  }
  

  We propose a passive methodology to estimate the queueing delay incurred by TCP traffic, and additionally leverage DPI classification to breakdown the delay across different applications. Ultimately, we correlate the queueing delay to the performance perceived by the users of that applications, depending on their delay-sensitivity. We implement our methodology in Tstat, and make it available 1 as open source software to the community. We validate and tune the tool, and run a preliminary measurement campaign based on a real ISP traffic trace, showing interesting yet partly counter-intuitive results.
• [ITC-13] Gong, YiXi and Rossi, Dario and Leonardi, Emilio, "Modeling the interdependency of low-priority congestion control and active queue management" The 25th International Teletraffic Congress (ITC25), Runner-up for Best Paper Award sep. 2013, Conference Runner-up Abstract Bibtex

  @inproceedings{DR:ITC-13,
    title = {Modeling the interdependency of low-priority congestion control and active queue management},
    author = {Gong, YiXi and Rossi, Dario and Leonardi, Emilio},
    booktitle = {The 25th International Teletraffic Congress (ITC25), Runner-up for Best Paper Award},
    year = {2013},
    month = sep,
    note = {bestpaperrunnerup},
    howpublished = {https://nonsns.github.io/paper/rossi13itc.pdf}
  }
  

  Recently, a negative interplay has been shown to arise when scheduling/AQM techniques and low-priority conges- tion control protocols are used together: namely, AQM resets the relative level of priority among congestion control protocols. This work explores this issue by (i) studying a fluid model that describes system dynamics of heterogeneous congestion control protocols competing on a bottleneck link governed by AQM and (ii) proposing a system level solution able to reinstate priorities among protocols.
• [CAMAD-13] Bellante, Walter and Vilardi, Rosa and Rossi, Dario, "On Netflix catalog dynamics and caching performance" IEEE CAMAD sep. 2013, Conference Abstract Bibtex

  @inproceedings{DR:CAMAD-13,
    title = {On Netflix catalog dynamics and caching performance},
    author = {Bellante, Walter and Vilardi, Rosa and Rossi, Dario},
    institution = {Telecom ParisTech},
    year = {2013},
    booktitle = {IEEE CAMAD},
    address = {Berlin, Germany},
    month = sep,
    howpublished = {https://nonsns.github.io/paper/rossi13camad.pdf}
  }
  

  Multimedia streaming applications have substantially changed the market policy of an increasing number of content providers that offer streaming services to the users. The need for effective video content delivery re-fueled interest for caching: since the Web-like workload of the 90s are not longer fit to describe the new Web of videos, in this work we investigate the suitability of the publicly available Netflix dataset for caching studies. Our analysis shows that, as the dataset continuously evolves (i) a steady state description is not statistically meaningful and (ii) despite the cache hit ratio decreases due to the growth of active movies in the catalog, simple caching replacement approaches are close to the optimum given the growing skew in the popularity distribution over the time. Additionally, we point out that, since the dataset reports logs of movie ratings, anomalies arise when ratings are considered to be movie views. At the same time, we show anomalies yield conservative caching results, that reinforces the soundness of our study.
• [P2P-13a] Testa, C. and Rossi, D. and Rao, A. and Legout, A., "Data Plane Throughput vs Control Plane Delay: Experimental Study of BitTorrent Performance" IEEE P2P’XIII sep. 2013, Conference Abstract Bibtex

  @inproceedings{DR:P2P-13a,
    title = {Data Plane Throughput vs Control Plane Delay: Experimental Study of BitTorrent Performance},
    author = {Testa, C. and Rossi, D. and Rao, A. and Legout, A.},
    year = {2013},
    booktitle = {IEEE P2P'XIII},
    address = {Trento, Italy},
    month = sep,
    howpublished = {https://nonsns.github.io/paper/rossi13p2p-a.pdf}
  }
  

  In this paper, we address the trade-off between the data plane efficiency and the control plane timeliness for the BitTorrent performance. We argue that loss-based congestion control protocols can fill large buffers, leading to a higher end-to-end delay, unlike low-priority or delay-based congestion control protocols. We perform experiments for both the uTorrent and mainline BitTorrent clients, and we study the impact of uTP (a novel transport protocol proposed by BitTorrent) and several TCP congestion control algorithms (Cubic, New Reno, LP, Vegas and Nice) on the download completion time. Briefly, in case peers in the swarm all use the same congestion control algorithm, we observe that the specific algorithm has only a limited impact on the swarm performance. Conversely, when a mix of TCP congestion control algorithms coexists, peers employing a delay-based low-priority algorithm exhibit shorter completion time.
• [P2P-13b] Rossi, D. and Nicolas, Y. and Wolff, D. and Finamore, A., "I tube, YouTube, P2PTube: assessing ISP benefits of peer-assisted caching of YouTube content" IEEE P2P’XIII sep. 2013, Conference Abstract Bibtex

  @inproceedings{DR:P2P-13b,
    title = {I tube, YouTube, P2PTube: assessing ISP benefits of peer-assisted caching of YouTube content},
    author = {Rossi, D. and Nicolas, Y. and Wolff, D. and Finamore, A.},
    institution = {Telecom ParisTech},
    year = {2013},
    booktitle = {IEEE P2P'XIII},
    address = {Trento, Italy},
    month = sep,
    howpublished = {https://nonsns.github.io/paper/rossi13p2p-b.pdf}
  }
  

  This paper proposes P2PTube, a very simple yet effective set-top-box system to assist diffusion of YouTube videos. We argue that, due to the spatial and temporal nature of video requests, the simplest design already provides non marginal gains. Our trace driven evaluation shows that, with moderate cache size (100MB) and nominal upload rates (500Kbps), about half of the video requests could be served by P2PTube. Interestingly, we also see that non marginal gains are already achievable with tiny caches – which is tied to the presence of advertisement prior that the actual video requested by the user.
• [TMA-13a] Chirichella, C. and Rossi, D., "To the Moon and back: are Internet bufferbloat delays really that large" IEEE INFOCOM Workshop on Traffic Measurement and Analysis (TMA’13) apr. 2013, Conference Abstract Bibtex

  @inproceedings{DR:TMA-13a,
    author = {Chirichella, C. and Rossi, D.},
    title = {To the Moon and back: are Internet bufferbloat delays really that large},
    booktitle = {IEEE INFOCOM Workshop on Traffic Measurement and Analysis (TMA'13)},
    year = {2013},
    address = {Turin, Italy},
    month = apr,
    howpublished = {https://nonsns.github.io/paper/rossi13tma-a.pdf}
  }
  

  Recently, the \u201cbufferbloat\u201d term has been coined to describe very large queuing delays (up to several seconds) experienced by Internet users. This problem has pushed protocol designer to deploy alternative (delay-based) models to the standard (lossbased) TCP best effort congestion control. In this work, we exploit timestamp information carried in the LEDBAT header, a protocol proposed by BitTorrent as replacement for TCP data transfer, to infer the queuing delay suffered by remote hosts. We conduct a thorough measurement campaign, that let us conclude that (i) LEDBAT delay-based congestion control is effective in keeping the queuing delay low for the bulk of the peers, (ii) yet about 1% of peers often experience queuing delay in excess of 1s, and (iii) not only the network access type, but also the BitTorrent client and the operating system concurr in determining the bufferbloat magnitude.
• [TMA-13b] Gong, Y. and Rossi, D. and Testa, C. and Valenti, S. and Taht, D., "Fighting the bufferbloat: on the coexistence of AQM and low priority congestion control" IEEE INFOCOM Workshop on Traffic Measurement and Analysis (TMA’13) apr. 2013, Conference Abstract Bibtex

  @inproceedings{DR:TMA-13b,
    author = {Gong, Y. and Rossi, D. and Testa, C. and Valenti, S. and Taht, D.},
    title = {Fighting the bufferbloat: on the coexistence of AQM and low priority congestion control},
    booktitle = {IEEE INFOCOM Workshop on Traffic Measurement and Analysis (TMA'13)},
    year = {2013},
    address = {Turin, Italy},
    month = apr,
    howpublished = {https://nonsns.github.io/paper/rossi13tma-b.pdf}
  }
  

  Nowadays, due to excessive queuing, delays on the Internet can grow longer than several round trips between the Moon and the Earth, for which the "bufferbloat" term was recently coined. Some point to active queue management (AQM) as the solution. Others propose end-to-end low-priority congestion control techniques (LPCC). Under both approaches, promising advances have been made in recent times: notable examples are CoDel for AQM, and LEDBAT for LPCC. In this paper, we warn of a potentially fateful interaction when AQM and LPCC techniques are combined: namely (i) AQM resets the relative level of priority between best effort and low-priority congestion control protocols; (ii) while reprioritization generally equalizes the priority of LPCC and TCP, we also find that some AQM settings may actually lead best effort TCP to starvation. By an extended set of experiments conducted on both controlled testbeds and on the Internet, we show the problem to hold in the real world for all tested combination of AQM policies and LPCC protocols. To further validate the generality of our findings, we complement our experiments with packet-level simulation, to cover cases of other popular AQM and LPCC that are not available in the Linux kernel. To promote cross-comparison, we make our scripts and dataset available to the research community.
• [PAM-13] Chirichella, C. and Rossi, D. and Testa, C. and Friedman, T. and Pescape, A., "Remotely Gauging Upstream Bufferbloat Delays" Passive and Active Measurement (PAM), Extended Abstract mar. 2013, Conference Abstract Bibtex

  @inproceedings{DR:PAM-13,
    author = {Chirichella, C. and Rossi, D. and Testa, C. and Friedman, T. and Pescape, A.},
    title = {Remotely Gauging Upstream Bufferbloat Delays},
    booktitle = {Passive and Active Measurement (PAM), Extended Abstract},
    year = {2013},
    address = {Hong Kong, China},
    month = mar,
    howpublished = {https://nonsns.github.io/paper/rossi13pam.pdf}
  }
  

  Bufferbloat is the growth in buffer size that has led Internet delays to occasionally exceed the light propagation delay from the Earth to the Moon. Manufacturers have built in large buffers to prevent losses on Wi-Fi, cable and ADSL links. But the combination of some links’ limited bandwidth with TCP’s tendency to saturate that bandwidth results in excessive queuing delays. In response, new congestion control protocols such as BitTorrent’s uTP/LEDBAT aim at explicitly limiting the delay that they add over the bottleneck link. This work proposes and validate a methodology to monitor the upstream queuing delay experienced by remote hosts, both those using LEDBAT, through LEDBAT’s native one-way delay measurements, and those using TCP (via the Timestamp Option).
• [TMA-13c] Valenti, Silvio and Rossi, Dario and Dainotti, Alberto and Pescape, Antonio and Finamore, Alessandro and Mellia, Marco, "Reviewing Traffic Classification" 2013, Bookch Bibtex

  @inbook{DR:TMA-13c,
    author = {Valenti, Silvio and Rossi, Dario and Dainotti, Alberto and Pescape, Antonio and Finamore, Alessandro and Mellia, Marco},
    title = {Reviewing Traffic Classification},
    editor = {Ernst Biersack, Christian Callegari, Maja Matijasevic},
    booktitle = {Data Traffic Monitoring and Analysis: From measurement, classification and anomaly detection to Quality of Experience},
    publisher = {Springer (LNCS 7754)},
    address = {Heidelberg, Germany},
    year = {2013},
    chapter = {6},
    howpublished = {https://nonsns.github.io/paper/rossi13tma-bookch.pdf}
  }
  
• [CONEXT-12] , "Interaction or Interference: can AQM and Low Priority Congestion Control Successfully Collaborate" ACM CoNEXT’12 Student Workshop dec. 2012, Conference Abstract Bibtex

  @inproceedings{DR:CONEXT-12,
    title = {Interaction or Interference: can AQM and Low Priority Congestion Control Successfully Collaborate},
    author = {},
    year = {2012},
    booktitle = {ACM CoNEXT'12 Student Workshop},
    month = dec,
    pages = {25-26},
    howpublished = {https://nonsns.github.io/paper/rossi12conext.pdf}
  }
  

  Heterogeneity in the Internet ecosystem sometimes turns interaction into interference. Over the years, active queue management (AQM) and end-to-end low-priority congestion control (LPCC) have been proposed as alternative solutions to counter the persistently full buffer problem – that recently became popular under the "bufferbloat" term. In this work, we point out the existence of a negative interplay among AQM and LPCC techniques. Intuitively, as AQM is designed to penalize the most aggressive flows it mainly hit best effort TCP: it follows that LPCC is not able to maintain its low priority, thus becoming as aggressive as TCP. By an extended set of simulation on various AQM policies and LPCC protocols, including the very recent CoDel AQM and LEDBAT LPCC proposals, we point out that this interference is quite universal and deserves further attention.
• [IMC-12] del Rio, P.M. Santiago and Rossi, D. and Gringoli, F. and Nava, L. and Salgarelli, L. and Aracil, J., "Wire-Speed Statistical Classification of Network Traffic on Commodity Hardware" ACM SIGCOMM Internet Measurement Conference (IMC) nov. 2012, Conference Abstract Bibtex

  @inproceedings{DR:IMC-12,
    title = {Wire-Speed Statistical Classification of Network Traffic on Commodity Hardware},
    author = {del Rio, P.M. Santiago and Rossi, D. and Gringoli, F. and Nava, L. and Salgarelli, L. and Aracil, J.},
    year = {2012},
    pages = {65-72},
    booktitle = {ACM SIGCOMM Internet Measurement Conference (IMC)},
    month = nov,
    howpublished = {https://nonsns.github.io/paper/rossi12imc.pdf}
  }
  

  In this paper we present a software-based traffic classification engine running on commodity multi-core hardware, able to process in real-time aggregates of up to 14.2 Mpps over a single 10 Gbps interface \u2013 i.e., the maximum possible packet rate over a 10 Gbps Ethernet links given the minimum frame size of 64 Bytes. This significant advance with respect to the current state of the art in terms of achieved classification rates are made possible by: (i) the use of an improved network driver, PacketShader, to efficiently move batches of packets from the NIC to the main CPU; (ii) the use of lightweight statistical classification techniques exploiting the size of the first few packets of every observed flow; (iii) a careful tuning of critical parameters of the hardware environment and the software application itself.

ANR Connect 8

• [ICN-13] , "INFORM: a Dynamic Interest Forwarding Mechanism for Information Centric Networking" ACM SIGCOMM Worskhop on Information-Centric Networking (ICN) 2013, Conference Abstract Bibtex

  @inproceedings{DR:ICN-13,
    title = {{INFORM: a Dynamic Interest Forwarding Mechanism for Information Centric Networking}},
    author = {},
    booktitle = {ACM SIGCOMM Worskhop on Information-Centric Networking (ICN)},
    year = {2013},
    address = {Hong Kong, China}
  }
  

  Information Centric Networking is a new communication paradigm where network primitives are based on named-data rather than host identifiers. In ICN, data retrieval is triggered by user requests which are forwarded towards a copy of the desired content item. Data can be retrieved either from a server that permanently provides a content item, or from a temporary item copy opportunistically cached by an in-network node. As the availability of cached items dynamically varies over time, the request forwarding scheme should be adapted accordingly. In this paper we focus on dynamic request forwarding in ICN, and develop an approach, inspired by Q-routing framework, that we show to outperform algorithms currently available in the state of the art.
• [COMCOM-13] Rossini, Giuseppe and Rossi, Dario, "Evaluating CCN multi-path interest forwarding strategies" In Elsevier Computer Communication, SI on Information Centric Networking,, Vol. 36, pp.771-778, Avril. 2013, Journal Abstract Bibtex

  @article{DR:COMCOM-13,
    author = {Rossini, Giuseppe and Rossi, Dario},
    title = {Evaluating CCN multi-path interest forwarding strategies},
    journal = {Elsevier Computer Communication, SI on Information Centric Networking,},
    month = {Avril},
    volume = {36},
    issue = {7},
    pages = {771-778},
    year = {2013}
  }
  

  This work addresses the performance evaluation of Content Centric Networks (CCN). Focusing on a realistic YouTube-like catalog, we conduct a thorough simulation study of the main system performance, with a special focus on multi-path interest forwarding strategies but thoroughly analyzing the impact of several other ingredients – such as network topology, content popularity, caching decisions and replacement policies. Summarizing our main results, (i) catalog and popularity settings play by far the most crucial role (ii) the impact of the strategy layer comes next, with naive forwarding strategies playing against CCN efficiency, (iii) simple randomized caching policies perform almost as well as more complex ones, (iv) the impact of the topology is limited. Hopefully, our thorough assessment of scenario parameters can assist and promote the cross-comparison in the research community – for which we also provide our CCN simulator as open source software.
• [CAMAD-12] G. Rossini, D. Rossi, "A dive into the caching performance of Content Centric Networking" IEEE 17th International Workshop on Computer Aided Modeling and Design of Communication Links and Networks (CAMAD’12) sep. 2012, Conference Abstract Bibtex

  @inproceedings{DR:CAMAD-12,
    title = {A dive into the caching performance of Content Centric Networking},
    author = {G. Rossini, D. Rossi},
    booktitle = {IEEE 17th International Workshop on Computer Aided Modeling and Design of Communication Links and Networks (CAMAD'12)},
    year = {2012},
    month = sep,
    pages = {105-109}
  }
  

  Content Centric Networking (CCN) is a promising architecture for the diffusion of popular content over the Internet. While CCN system design is sound, gathering a reliable estimate of its performance in the current Internet is challenging, due to the large scale and to the lack of agreement in some critical elements of the evaluation scenario. In this work, we add a number of important pieces to the CCN puzzle by means of a chunk-level simulator that we make available to the scientific community as open source software. First, we pay special attention to the locality of the user request process, as it may be determined by user interest or language barrier. Second, we consider the existence of possibly multiple repositories for the same content, as in the current Internet, along with different CCN interest forwarding policies, exploiting either a single or multiple repositories in parallel. To widen the relevance of our findings, we consider multi- ple topologies, content popularity settings, caching replacement policies and CCN forwarding strategies. Summarizing our main result, though the use of multiple content repositories can be beneficial from the user point of view, it may however counter part of the benefits if the CCN strategy layer implements naive interest forwarding policies.
• [ALGOTEL-12] Rossini, G. and Rossi, D., "Large scale simulation of CCN networks" Algotel 2012 may. 2012, Conference Abstract Bibtex

  @inproceedings{DR:ALGOTEL-12,
    author = {Rossini, G. and Rossi, D.},
    title = {Large scale simulation of CCN networks},
    booktitle = {Algotel 2012},
    year = {2012},
    address = {La Grande Motte, France},
    month = may
  }
  

  This work addresses the performance evaluation of Content Centric Networks (CCN). Focusing on a realistic YouTube-like catalog, we conduct a very thorough simulation study of the main system performance, consider several ingredients such as network topology, multi-path routing, content popularity, caching decisions and replacement policies. Summarizing our main results, we gather that (i) the impact of the topology is limited, (ii) multi-path routing may play against CCN efficiency, (iii) simple randomized policies perform almost as well as more complex ones, (iv) catalog and popularity settings play by far the most crucial role above all. Hopefully, our thorough assessment of scenario parameters can assist and promote the cross-comparison in the research community – for which we also provide our CCN simulator as open source software.
• [NOMEN-12] Rossi, D. and Rossini, G., "On sizing CCN content stores by exploiting topological information" IEEE INFOCOM, NOMEN Worshop, mar. 2012, Conference Abstract Bibtex

  @inproceedings{DR:NOMEN-12,
    author = {Rossi, D. and Rossini, G.},
    title = {On sizing CCN content stores by exploiting topological information},
    booktitle = {IEEE INFOCOM, NOMEN Worshop,},
    year = {2012},
    address = {Orlando, FL},
    pages = {280-285},
    month = mar
  }
  

  In this work, we study the caching performance of Content Centric Networking (CCN), with special emphasis on the size of individual CCN router caches. Specifically, we consider several graph-related centrality metrics (e.g., betweenness, closeness, stress, graph, eccentricity and degree centralities) to allocate content store space heterogeneously across the CCN network, and contrast the performance to that of an homogeneous allocation. To gather relevant results, we study CCN caching performance under large cache sizes (individual content stores of 10 GB), realistic topologies (up to 60 nodes), a YouTube-like Internet catalog (108 files for 1PB video data). A thorough simulation campaign allow us to conclude that (i) , the gain brought by content store size heterogeneity is very limited, and that (ii) the simplest metric, namely degree centrality, already proves to be a “sufficiently good” allocation criterion. On the one hand, this implies rather simple rules of thumb for the content store sizing (e.g., “if you add a line card to a CCN router, add some content store space as well”). On the other hand, we point out that technological constraints, such as line- speed operation requirement, may however limit the applicability of degree-based content store allocation.
• [IETF83-a] Rossi, Dario, "A dive into CCN^⋆caching performance" Talk at IETF83, ICNRG meeting mar. 2012, Conference Bibtex

  @inproceedings{DR:IETF83-a,
    author = {Rossi, Dario},
    title = {A dive into CCN$^\star$ caching performance},
    booktitle = {Talk at IETF83, ICNRG meeting},
    month = mar,
    year = {2012}
  }
  
• [ICN-12] Chiocchetti, Raffaele and Rossi, Dario and Rossini, Giuseppe and Carofiglio, Giovanna and Diego Perino, "Exploit the known or explore the unknown: Hamlet-like doubts in ICN" ACM SIGCOMM, ICN Workshop, 2012, Conference Bibtex

  @inproceedings{DR:ICN-12,
    author = {Chiocchetti, Raffaele and Rossi, Dario and Rossini, Giuseppe and Carofiglio, Giovanna and Diego Perino},
    title = {Exploit the known or explore the unknown: Hamlet-like doubts in ICN},
    booktitle = {ACM SIGCOMM, ICN Workshop,},
    year = {2012}
  }
  
• [CCN-TR11a] D. Rossi, G. Rossini, "Caching performance of content centric networks under multi-path routing (and more)" Telecom ParisTech 2011, Tech.Rep. Bibtex

  @techreport{DR:CCN-TR11a,
    title = {Caching performance of content centric networks under multi-path routing (and more)},
    author = {D. Rossi, G. Rossini},
    institution = {Telecom ParisTech},
    year = {2011}
  }
  

EIT ICTLabs SmartUC 1

• [ICC-13] Chiocchetti, Raffaele and Rossi, Dario and Rossini, Giuseppe, "ccnSim: an Highly Scalable CCN Simulator" IEEE International Conference on Communications (ICC) jun. 2013, Conference Abstract Bibtex

  @inproceedings{DR:ICC-13,
    title = {{ccnSim}: an Highly Scalable CCN Simulator},
    author = {Chiocchetti, Raffaele and Rossi, Dario and Rossini, Giuseppe},
    booktitle = {IEEE International Conference on Communications (ICC)},
    year = {2013},
    month = jun,
    howpublished = {https://nonsns.github.io/paper/rossi13icc.pdf}
  }
  

  Research interest about Information Centric Networking (ICN) has grown at a very fast pace over the last few years, especially after the 2009 seminal paper of Van Jacobson et al. describing a Content Centric Network (CCN) architecture. While significant research effort has been produced in terms of architectures, algorithms, and models, the scientific community currently lacks common tools and scenarios to allow a fair cross- comparison among the different proposals. The situation is particularly complex as the commonly used general-purpose simulators cannot cope with the expected system scale: thus, many proposals are currently evaluated over small and unrealistic scale, especially in terms of dominant factors like catalog and cache sizes. As such, there is need of a scalable tool under which different algorithms can be tested and compared. Over the last years, we have developed and optimized ccnSim, an highly scalable chunk-level simulator especially suitable for the analysis of caching performance of CCN network. In this paper, we briefly describe the tool, and present an extensive benchmark of its performance. To give an idea of ccnSim scalability, a common off-the-shelf PC equipped with 8GB of RAM memory is able to simulate 2-hours of a 50-nodes CCN network, where each nodes is equipped with 10 GB caches, serving a 1 PB catalog in about 20 min CPU time.

FP7 NapaWine 15

• [PPNA-13] Rossi, Dario and Veglia, Paolo and Sammarco, Matteo and Larroca, Federico, "ModelNet-TE: An emulation tool for the study of P2P and Traffic Engineering interaction dynamics" In Springer Peer-to-peer Networking and Applications (PPNA), Vol. 6, pp.194-212, 2013, Journal Abstract Bibtex

  @article{DR:PPNA-13,
    author = {Rossi, Dario and Veglia, Paolo and Sammarco, Matteo and Larroca, Federico},
    title = {ModelNet-TE: An emulation tool for the study of P2P and Traffic Engineering interaction dynamics},
    journal = {Springer Peer-to-peer Networking and Applications (PPNA)},
    year = {2013},
    volume = {6},
    issue = {2},
    pages = {194-212},
    howpublished = {https://nonsns.github.io/paper/rossi13ppna.pdf}
  }
  

  In the Internet, user-level performance of P2P applications may be determined by the interaction of two independent dynamics: on the one hand, by the end-to-end control policies applied at the P2P application layer (L7); on the other hand, by Traffic Engineering (TE) decisions taken at the network level (L3). Currently available tools do not allow to study L7/L3 interactions in realistic settings due to a number of limitations. Building over ModelNet, we develop a framework for the real-time emulation of TE capabilities, named ModelNet-TE, that we make available to the scientific community as open source software. ModelNet-TE allows (i) to deploy real unmodified Internet P2P applications, and to test their interaction with (ii) many TE algorithms, as its design allows to easily integrate other TE algorithms than those we already provide, (iii) in a furthermore controlled network environment. Due to these features, ModelNet-TE is a complementary tool with respect to hybrid simulation/protoyping toolkits (that constrain application development to a specific language and framework, and cannot be used with existing or proprietary applications) and to other open testbeds such as PlanetLab or Grid5000 (lacking of control or TE-capabilities respectively). ModelNet-TE can thus be useful to L7-researchers, as it allows to seamlessly and transparently test any existing P2P application without requiring any software modification. At the same time, ModelNet-TE can be useful to L3-researchers as well, since they can test their TE algorithms on the traffic generated by real applications. As a use case, in this work we carry on an experimental campaign of L7/L3 routing layers interaction through ModelNet-TE. As TE we consider the classic minimum congestion load-balancing, that we compare against standard IP routing. As example P2P applications, we take BitTorrent, one among the most popular file-sharing applications nowadays, and WineStreamer, an open source live-streaming application. We emulate BitTorrent and WineStreamer swarms over both realistic topologies (e.g., Abilene) and simplistic topologies that are commonly in use today (e.g., where the bottleneck is located at the network edge) under a variety of scenarios. Results of our experimental campaign show that user-level performance may be significantly affected by both the TE mechanism in use at L3 (e.g., due to interactions with TCP congestion control or P2P chunk trading logic), as well as scenario parameters that are difficult to control in the wild Internet, which thus testifies the interest for tools such as ModelNet-TE.
• [PPNA-12] Paolo Veglia, Dario Rossi, "Performance evaluation of P2P-TV diffusion algorithms under realistic settings" In Springer Peer-to-peer Networking and Applications (PPNA), Vol. 6, pp.26-45, 2012, Journal Abstract Bibtex

  @article{DR:PPNA-12,
    author = {Paolo Veglia, Dario Rossi},
    title = {Performance evaluation of P2P-TV diffusion algorithms under realistic settings},
    journal = {Springer Peer-to-peer Networking and Applications (PPNA)},
    year = {2012},
    volume = {6},
    issue = {1},
    pages = {26-45},
    howpublished = {https://nonsns.github.io/paper/rossi12ppna.pdf}
  }
  

  Internet video and peer-to-peer television (P2P-TV) are attracting more and more users: chances are that P2P-TV is going to be the next Internet killer application. In recent years, valuable effort has been devoted to the problems of chunk-scheduling and overlay management in P2P-TV systems. However, many interesting P2P-TV proposals have been evaluated either in rather idealistic environments, or in the wild Internet. Our work sits in between these two antipodean approaches: our aim is to compare existing systems in a controlled way, but taking special care in realistic conditions for their evaluation at the same time. We carry on a simulation analysis that considers several factors, modeling the L7 overlay (e.g., chunk scheduling, topology management, overlay topology, etc.), the L3 network (e.g., end-to-end latency models, fixed vs dynamic conditions, etc.), and the interaction of both layers (e.g., measurement errors, loss of signaling messages, etc.). To depict a comprenshive system view, results are expressed in terms of both user-centric and network-centric metrics. In a nuthshell, our main finding is that P2P-TV systems are generally robust against measurement errors (e.g., propagation delay or capacity estimation), but are on the contrary deeply affected by signaling errors (e.g., loss or outdated system view), which are often overlooked without justification.
• [COMNET-11] Bermolen, P. and M.Mellia and Meo, M. and Rossi, D. and Valenti, S., "Abacus: Accurate, Fine-Grained Classification of P2P-TV Traffic" In Elsevier Computer Networks, pp.1394-1411, apr. 2011, Journal Bibtex

  @article{DR:COMNET-11,
    author = {Bermolen, P. and M.Mellia and Meo, M. and Rossi, D. and Valenti, S.},
    title = {Abacus: Accurate, Fine-Grained Classification of P2P-TV Traffic},
    journal = {Elsevier Computer Networks},
    year = {2011},
    month = apr,
    issue = {6},
    pages = {1394-1411},
    howpublished = {https://nonsns.github.io/paper/rossi11comnet.pdf}
  }
  
• [NTMS-11] Veglia, P. and Rossi, D., "Assessing the impact of signaling on the QoE of push-based P2P-TV diffusion algorithms" 4th IFIP International Conference on New Technologies, Mobility and Security (NTMS’11) 7-10 February. 2011, Conference Bibtex

  @inproceedings{DR:NTMS-11,
    author = {Veglia, P. and Rossi, D.},
    title = {Assessing the impact of signaling on the QoE of push-based P2P-TV diffusion algorithms},
    booktitle = {4th IFIP International Conference on New Technologies, Mobility and Security (NTMS'11)},
    year = {2011},
    address = {Paris, France},
    month = {7-10 February},
    howpublished = {https://nonsns.github.io/paper/rossi11ntms.pdf}
  }
  
• [TON-10] Finamore, A. and Mellia, M. and Meo, M. and Rossi, D., "KISS: Stochastic Packet Inspection Classifier for UDP Traffic" In IEEE Transactions on Networking, Vol. 18, No. 5, pp.1505 – 1515, oct. 2010, Journal Bibtex

  @article{DR:TON-10,
    author = {Finamore, A. and Mellia, M. and Meo, M. and Rossi, D.},
    title = {KISS: Stochastic Packet Inspection Classifier for UDP Traffic},
    journal = {IEEE Transactions on Networking},
    month = oct,
    year = {2010},
    volume = {18},
    number = {5},
    pages = {1505 -- 1515},
    howpublished = {https://nonsns.github.io/paper/rossi10ton.pdf}
  }
  
• [TRAC-10] Rossi, D. and Valenti, S., "Fine-grained traffic classification with Netflow data" ACM IWCMC 2010, 1st International Workshop on TRaffic Analysis and Classification (TRAC) jun. 2010, Conference Bibtex

  @inproceedings{DR:TRAC-10,
    author = {Rossi, D. and Valenti, S.},
    title = {{Fine-grained traffic classification with Netflow data}},
    booktitle = {ACM IWCMC 2010, 1st International Workshop on TRaffic Analysis and Classification (TRAC)},
    address = {Caen France,},
    year = {2010},
    month = jun,
    howpublished = {https://nonsns.github.io/paper/rossi10trac.pdf}
  }
  
• [TMA-10] Finamore, A. and Mellia, M. and Meo, M. and Rossi, D. and Valenti, S., "Kiss to Abacus: a comparison of P2P-TV traffic classifiers" Traffic Measurement and Analyis (TMA’10), LNCS apr. 2010, Conference Bibtex

  @inproceedings{DR:TMA-10,
    author = {Finamore, A. and Mellia, M. and Meo, M. and Rossi, D. and Valenti, S.},
    title = {{Kiss to Abacus: a comparison of P2P-TV traffic classifiers}},
    booktitle = {Traffic Measurement and Analyis (TMA'10), LNCS},
    address = {Zurich, Switzerland},
    year = {2010},
    month = apr,
    howpublished = {https://nonsns.github.io/paper/rossi10tma.pdf}
  }
  
• [TMM-10] Horvath, A. and Telek, M. and Rossi, D. and Veglia, P. and Ciullo, D. and da Rocha Neta, A. G. and Leonardi, E. and Mellia, M., "Network Awareness of P2P Live Streaming Applications: a Measurement Study" In IEEE Transactions on Multimedia, Vol. 12, No. 1, pp.54-63, jan. 2010, Journal Bibtex

  @article{DR:TMM-10,
    author = {Horvath, A. and Telek, M. and Rossi, D. and Veglia, P. and Ciullo, D. and da Rocha Neta, A. G. and Leonardi, E. and Mellia, M.},
    title = {Network Awareness of P2P Live Streaming Applications: a Measurement Study},
    journal = {IEEE Transactions on Multimedia},
    volume = {12},
    number = {1},
    pages = {54-63},
    year = {2010},
    month = jan,
    howpublished = {https://nonsns.github.io/paper/rossi10tmm.pdf}
  }
  
• [IJDMB-10] Rossi, D. and Veglia, P., "An Hybrid Approach to Assess the Network Awareness of P2P-TV Applications" In International Journal of Digital Multimedia Broadcasting, special issue on Network-Aware Peer-to-Peer (P2P) and Internet Video, Vol. doi:10.1155/2010/826351, . 2010, Journal Bibtex

  @article{DR:IJDMB-10,
    author = {Rossi, D. and Veglia, P.},
    title = {An Hybrid Approach to Assess the Network Awareness of P2P-TV Applications},
    journal = {International Journal of Digital Multimedia Broadcasting, special issue on Network-Aware Peer-to-Peer (P2P) and Internet Video},
    year = {2010},
    month = {},
    volume = {doi:10.1155/2010/826351},
    howpublished = {https://nonsns.github.io/paper/rossi10ijdmb.pdf}
  }
  
• [SIGCOMM-09] Rossi, D. and Sottile, E. and Valenti, S. and Veglia, P., "Gauging the network friendliness of P2P applications" ACM SIGCOMM, Demo Session aug. 2009, Conference Bibtex

  @inproceedings{DR:SIGCOMM-09,
    author = {Rossi, D. and Sottile, E. and Valenti, S. and Veglia, P.},
    title = {Gauging the network friendliness of P2P applications},
    booktitle = {ACM SIGCOMM, Demo Session},
    address = {Barcelona, Spain},
    year = {2009},
    month = aug,
    howpublished = {https://nonsns.github.io/paper/rossi09sigcomm.pdf}
  }
  
• [HOTP2P-09] Horvath, A. and Telek, M. and Rossi, D. and Veglia, P. and Ciullo, D. and Garcia, M. A. and Leonardi, E. and Mellia, M., "Network Awareness of P2P Live Streaming Applications" HOTP2P Workshop at IEEE IPDPS’09 may. 2009, Conference Bibtex

  @inproceedings{DR:HOTP2P-09,
    author = {Horvath, A. and Telek, M. and Rossi, D. and Veglia, P. and Ciullo, D. and Garcia, M. A. and Leonardi, E. and Mellia, M.},
    title = {Network Awareness of P2P Live Streaming Applications},
    booktitle = {HOTP2P Workshop at IEEE IPDPS'09},
    address = {Rome, Italy},
    year = {2009},
    month = may,
    howpublished = {https://nonsns.github.io/paper/rossi09hotp2p.pdf}
  }
  
• [TMA-09b] Finamore, A. and Mellia, M. and Meo, M. and Rossi, D., "KISS: Stochastic Packet Inspection" Traffic Measurement and Analysis (TMA), Springer-Verlag LNCS 5537 may. 2009, Conference Bibtex

  @inproceedings{DR:TMA-09b,
    author = {Finamore, A. and Mellia, M. and Meo, M. and Rossi, D.},
    title = {KISS: Stochastic Packet Inspection},
    booktitle = {Traffic Measurement and Analysis (TMA), Springer-Verlag LNCS 5537},
    year = {2009},
    month = may,
    howpublished = {https://nonsns.github.io/paper/rossi09tma-b.pdf}
  }
  
• [TMA-09a] Valenti, S. and Rossi, D. and Meo, M. and M.Mellia and Bermolen, P., "Accurate and Fine-Grained Classification of P2P-TV Applications by Simply Counting Packets" Traffic Measurement and Analysis (TMA), Springer-Verlag LNCS 5537 may. 2009, Conference Bibtex

  @inproceedings{DR:TMA-09a,
    author = {Valenti, S. and Rossi, D. and Meo, M. and M.Mellia and Bermolen, P.},
    title = {Accurate and Fine-Grained Classification of P2P-TV Applications by Simply Counting Packets},
    booktitle = {Traffic Measurement and Analysis (TMA), Springer-Verlag LNCS 5537},
    year = {2009},
    month = may,
    pages = {84--92},
    howpublished = {https://nonsns.github.io/paper/rossi09tma-a.pdf}
  }
  
• [INFOCOM-09] Valenti, S. and Rossi, D. and Meo, M. and Mellia, M. and Bermolen, P., "An Abacus for P2P-TV traffic classification" IEEE INFOCOM, Demo Session apr. 2009, Conference Bibtex

  @inproceedings{DR:INFOCOM-09,
    author = {Valenti, S. and Rossi, D. and Meo, M. and Mellia, M. and Bermolen, P.},
    title = {An Abacus for P2P-TV traffic classification},
    booktitle = {IEEE INFOCOM, Demo Session},
    address = {Rio de Janeiro, Brazil},
    year = {2009},
    month = apr,
    howpublished = {https://nonsns.github.io/paper/rossi09infocom.pdf}
  }
  
• [COMMAG-08] Leonardi, E. and Mellia, M. and Horvath, A. and Muscariello, L. and Niccolini, S. and Rossi, D., "Building a cooperative P2P-TV application over a Wise Network: the approach of the European FP-7 STREP NAPA-WINE" In IEEE Communication Magazine, Vol. 64, No. 6, apr. 2008, Journal Bibtex

  @article{DR:COMMAG-08,
    author = {Leonardi, E. and Mellia, M. and Horvath, A. and Muscariello, L. and Niccolini, S. and Rossi, D.},
    title = {Building a cooperative P2P-TV application over a Wise Network: the approach of the European FP-7 STREP NAPA-WINE},
    journal = {IEEE Communication Magazine},
    year = {2008},
    month = apr,
    volume = {64},
    number = {6},
    howpublished = {https://nonsns.github.io/paper/rossi08commag.pdf}
  }
  

Celtic Trans 13

• [P2P-11] Testa, C. and Rossi, D., "The impact of uTP on BitTorrent completion time" IEEE Peer to Peer (P2P’11) sep. 2011, Conference Bibtex

  @inproceedings{DR:P2P-11,
    author = {Testa, C. and Rossi, D.},
    title = {The impact of uTP on BitTorrent completion time},
    booktitle = {IEEE Peer to Peer (P2P'11)},
    year = {2011},
    month = sep,
    address = {Kyoto, Japan},
    howpublished = {https://nonsns.github.io/paper/rossi11p2p.pdf}
  }
  
• [TRAC-11] Valenti, S. and Rossi, D., "Fine-grained behavioral classification in the core: the issue of flow sampling" IEEE International Workshop on TRaffic Analysis and Classification (TRAC’11) 5-9 July. 2011, Conference Bibtex

  @inproceedings{DR:TRAC-11,
    author = {Valenti, S. and Rossi, D.},
    title = {Fine-grained behavioral classification in the core: the issue of flow sampling},
    booktitle = {IEEE International Workshop on TRaffic Analysis and Classification (TRAC'11)},
    year = {2011},
    month = {5-9 July},
    address = {Istanbul, Turkey},
    howpublished = {https://nonsns.github.io/paper/rossi11trac.pdf}
  }
  
• [ICC-11] Valenti, S. and Rossi, D., "Identifying key features for P2P traffic classification" IEEE International Conference on Communications (ICC’11) 5-9 June. 2011, Conference Bibtex

  @inproceedings{DR:ICC-11,
    author = {Valenti, S. and Rossi, D.},
    title = {Identifying key features for P2P traffic classification},
    booktitle = {IEEE International Conference on Communications (ICC'11)},
    year = {2011},
    month = {5-9 June},
    address = {Kyoto, Japan},
    howpublished = {https://nonsns.github.io/paper/rossi11icc.pdf}
  }
  
• [GLOBECOM-10b] Finamore, Alessandro and Mellia, Marco and Meo, Michela and Rossi, Dario and Valenti, Silvio, "Peer-to-peer traffic classification: exploiting human communication dynamics" IEEE Globecom’10, Demo Session dec. 2010, Conference Bibtex

  @inproceedings{DR:GLOBECOM-10b,
    title = {Peer-to-peer traffic classification: exploiting human communication dynamics},
    author = {Finamore, Alessandro and Mellia, Marco and Meo, Michela and Rossi, Dario and Valenti, Silvio},
    booktitle = {IEEE Globecom'10, Demo Session},
    address = {Miami, FL, USA},
    month = dec,
    year = {2010},
    howpublished = {https://nonsns.github.io/paper/rossi10globecom-b.pdf}
  }
  
• [GLOBECOM-10a] Carofiglio, G. and Muscariello, L. and Rossi, D. and Valenti, S., "The quest for LEDBAT fairness" IEEE Globecom’10 dec. 2010, Conference Bibtex

  @inproceedings{DR:GLOBECOM-10a,
    title = {The quest for LEDBAT fairness},
    author = {Carofiglio, G. and Muscariello, L. and Rossi, D. and Valenti, S.},
    booktitle = {IEEE Globecom'10},
    address = {Miami, FL, USA},
    month = dec,
    year = {2010},
    howpublished = {https://nonsns.github.io/paper/rossi10globecom-a.pdf}
  }
  
• [LCN-10] Carofiglio, G. and Muscariello, L. and Rossi, D. and Testa, C., "A hands-on Assessment of Transport Protocols with Lower than Best Effort Priority" 35th IEEE Conference on Local Computer Networks (LCN’10) oct. 2010, Conference Bibtex

  @inproceedings{DR:LCN-10,
    title = {A hands-on Assessment of Transport Protocols with Lower than Best Effort Priority},
    author = {Carofiglio, G. and Muscariello, L. and Rossi, D. and Testa, C.},
    booktitle = {35th IEEE Conference on Local Computer Networks (LCN'10)},
    address = {Denver, CO, USA},
    month = oct,
    year = {2010},
    howpublished = {https://nonsns.github.io/paper/rossi10lcn.pdf}
  }
  
• [ITC22-10] Pescape, A. and Rossi, D. and Tammaro, D. and Valenti, S., "On the impact of sampling on traffic monitoring and analysis" Proceedings of the 22nd International Teletraffic Congress (ITC22) sep. 2010, Conference Bibtex

  @inproceedings{DR:ITC22-10,
    title = {{On the impact of sampling on traffic monitoring and analysis}},
    author = {Pescape, A. and Rossi, D. and Tammaro, D. and Valenti, S.},
    booktitle = {Proceedings of the 22nd International Teletraffic Congress (ITC22)},
    address = {Amsterdam, The Netherlands},
    month = sep,
    year = {2010},
    howpublished = {https://nonsns.github.io/paper/rossi10itc22.pdf}
  }
  
• [ICCCN-10] Rossi, D. and Testa, C. and Valenti, S. and Muscariello, L., "LEDBAT: the new BitTorrent congestion control protocol" International Conference on Computer Communication Networks (ICCCN’10) aug. 2010, Conference Bibtex

  @inproceedings{DR:ICCCN-10,
    title = {LEDBAT: the new BitTorrent congestion control protocol},
    author = {Rossi, D. and Testa, C. and Valenti, S. and Muscariello, L.},
    booktitle = {International Conference on Computer Communication Networks (ICCCN'10)},
    address = {Zurich, Switzerland},
    month = aug,
    year = {2010},
    howpublished = {https://nonsns.github.io/paper/rossi10icccn.pdf}
  }
  
• [ICC-10] Mantia, G. La and Rossi, D. and Finamore, A. and Mellia, M. and Meo, M., "Stochastic Packet Inspection for TCP Traffic" IEEE International Conference on Communications (ICC’10) may. 2010, Conference Bibtex

  @inproceedings{DR:ICC-10,
    author = {Mantia, G. La and Rossi, D. and Finamore, A. and Mellia, M. and Meo, M.},
    title = {{Stochastic Packet Inspection for TCP Traffic}},
    booktitle = {IEEE International Conference on Communications (ICC'10)},
    address = {Cape Town, South Africa},
    year = {2010},
    month = may,
    howpublished = {https://nonsns.github.io/paper/rossi10icc.pdf}
  }
  
• [PAM-10] Rossi, D. and Testa, C. and Valenti, S., "Yes, we LEDBAT: Playing with the new BitTorrent congestion control algorithm" Passive and Active Measurement (PAM’10) apr. 2010, Conference Bibtex

  @inproceedings{DR:PAM-10,
    author = {Rossi, D. and Testa, C. and Valenti, S.},
    title = {{Yes, we LEDBAT: Playing with the new BitTorrent congestion control algorithm}},
    booktitle = {Passive and Active Measurement (PAM'10)},
    address = {Zurich, Switzerland},
    year = {2010},
    month = apr,
    howpublished = {https://nonsns.github.io/paper/rossi10pam.pdf}
  }
  
• [TECHREP-10] Rossi, Dario and Testa, C. and Valenti, S. and Veglia, P. and Muscariello, L., "News from the Internet congestion control world" Telecom ParisTech 2010, Tech.Rep. Bibtex

  @techreport{DR:TECHREP-10,
    title = {News from the Internet congestion control world},
    author = {Rossi, Dario and Testa, C. and Valenti, S. and Veglia, P. and Muscariello, L.},
    institution = {Telecom ParisTech},
    year = {2010},
    howpublished = {http://arxiv.org/pdf/0908.0812}
  }
  
• [PPNA-10] Rossi, D. and Sottile, E. and Veglia, P., "Black-box analysis of Internet P2P applications" In Peer-to-Peer Networking and Applications, pp.1-19, 2010, Journal Bibtex

  @article{DR:PPNA-10,
    author = {Rossi, D. and Sottile, E. and Veglia, P.},
    title = {Black-box analysis of Internet P2P applications},
    year = {2010},
    journal = {Peer-to-Peer Networking and Applications},
    publisher = {Springer New York},
    issn = {1936-6442},
    pages = {1-19},
    howpublished = {https://nonsns.github.io/paper/rossi10ppna.pdf}
  }
  
• [P2P-09] Rossi, D. and Sottile, E., "Sherlock: A framework for P2P traffic analysis" IEEE P2P’09 sep. 2009, Conference Bibtex

  @inproceedings{DR:P2P-09,
    author = {Rossi, D. and Sottile, E.},
    title = {Sherlock: A framework for P2P traffic analysis},
    booktitle = {IEEE P2P'09},
    address = {Seattle, WA, USA},
    year = {2009},
    month = sep,
    howpublished = {https://nonsns.github.io/paper/rossi09p2p.pdf}
  }
  

Celtic Tiger and Tiger2 0

Other projects 119

• [PAM-18a] Salutari, Flavia and Cicalese, Danilo and Rossi, Dario, "A closer look at IP-ID behavior in the Wild" International Conference on Passive and Active Network Measurement (PAM) mar. 2018, Conference Abstract Bibtex

  @inproceedings{DR:PAM-18a,
    title = {A closer look at IP-ID behavior in the Wild},
    author = {Salutari, Flavia and Cicalese, Danilo and Rossi, Dario},
    booktitle = {International Conference on Passive and Active Network Measurement (PAM)},
    address = {Berlin, Germany},
    year = {2018},
    month = mar,
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/rossi18pam-a.pdf}
  }
  

  Originally used to assist network-layer fragmentation and reassembly, the IP identification field (IP-ID) has been used and abused for a range of tasks, from counting hosts behind NAT, to detect router aliases and, lately, to assist detection of censorship in the Internet at large. These inferences have been possible since, in the past, the IP- ID was mostly implemented as a simple packet counter: however, this behavior has been discouraged for security reasons and other policies, such as random values, have been suggested. In this study, we propose a framework to classify the different IP-ID behaviors using active probing from a single host. Despite being only minimally intrusive, our technique is significantly accurate (99% true positive classification) robust against packet losses (up to 20%) and lightweight (few packets suffices to discriminate all IP-ID behaviors). We then apply our technique to an Internet-wide census, where we actively probe one alive target per each routable /24 subnet: we find that that the majority of hosts adopts a constant IP-IDs (39%) or local counter (34%), that the fraction of global counters (18%) significantly diminished, that a non marginal number of hosts have an odd behavior (7%) and that random IP-IDs are still an exception (2%).
• [PAM-18b] da Hora, Diego Neves and Asrese, Alemnew Sheferaw and Christophides, Vassilis and Teixeira, Renata and Rossi, Dario, "Narrowing the gap between QoS metrics and Web QoE using Above-the-fold metrics" International Conference on Passive and Active Network Measurement (PAM), Receipient of the Best dataset award mar. 2018, Conference Abstract Bibtex

  @inproceedings{DR:PAM-18b,
    title = {Narrowing the gap between QoS metrics and Web QoE using Above-the-fold metrics},
    author = {da Hora, Diego Neves and Asrese, Alemnew Sheferaw and Christophides, Vassilis and Teixeira, Renata and Rossi, Dario},
    booktitle = {International Conference on Passive and Active Network Measurement (PAM), Receipient of the Best dataset award},
    address = {Berlin, Germany},
    month = mar,
    year = {2018},
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/rossi18pam-b.pdf}
  }
  

  Page load time (PLT) is still the most common application Quality of Service (QoS) metric to estimate the Quality of Experience (QoE) of Web users. Yet, recent literature abounds with proposals for alternative metrics (e.g., Above The Fold, SpeedIndex and their variants) that aim at better estimating user QoE. The main purpose of this work is thus to thoroughly investigate a mapping between established and recently proposed objective metrics and user QoE. We obtain ground truth QoE via user experiments where we collect and analyze 3,400 Web accesses annotated with QoS metrics and explicit user ratings in a scale of 1 to 5, which we make available to the community. In particular, we contrast domain expert models (such as ITU-T and IQX) fed with a single QoS metric, to models trained using our ground-truth dataset over multiple QoS metrics as features. Results of our experiments show that, albeit very simple, expert models have a comparable accuracy to machine learning approaches. Furthermore, the model accuracy improves considerably when building per-page QoE models, which may raise scalability concerns as we discuss.
• [PAM-18c] Green, Thomas and Lambert, Anthony and Pelsser, Cristel and Rossi, Dario, "Leveraging Inter-domain Stability for BGP Dynamics Analysis" International Conference on Passive and Active Network Measurement (PAM) mar. 2018, Conference Abstract Bibtex

  @inproceedings{DR:PAM-18c,
    title = {{Leveraging Inter-domain Stability for BGP Dynamics Analysis}},
    author = {Green, Thomas and Lambert, Anthony and Pelsser, Cristel and Rossi, Dario},
    booktitle = {International Conference on Passive and Active Network Measurement (PAM)},
    address = {Berlin, Germany},
    year = {2018},
    month = mar,
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/rossi18pam-c.pdf}
  }
  

  In the Internet, Autonomous Systems continuously exchange routing information via the BGP protocol: the large number of networks involved and the verbosity of BGP result in a huge stream of updates. Making sense of all those messages remains a challenge today. In this paper, we leverage the notion of "primary path" (i.e., the most used inter-domain path of a BGP router toward a destination prefix for a given time period), reinterpreting updates by grouping them in terms of primary paths unavailability periods, and illustrate how BGP dynamics analysis would benefit from working with primary paths. Our contributions are as follows. First, through measurements, we validate the existence of primary paths: by analyzing BGP updates announced at the LINX RIS route collector spanning a three months period, we show that primary paths are consistently in use during the observation period. Second, we quantify the benefits of primary paths for BGP dynamics analysis on two use cases : Internet tomography and anomaly detection. For the latter, using three months of anomalous BGP events documented by BGPmon as reference, we show that primary paths could be used for detecting such events (hijacks and outages), testifying of the increased semantic they provide.
• [CCR-18] Cicalese, Danilo and Rossi, Dario, "A longitudinal study of IP Anycast" In ACM Computer Communication Review, Vol. to appear, 2018, Journal Abstract Bibtex

  @article{DR:CCR-18,
    title = {A longitudinal study of IP Anycast},
    author = {Cicalese, Danilo and Rossi, Dario},
    journal = {ACM Computer Communication Review},
    volume = {to appear},
    year = {2018},
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/rossi18ccr.pdf}
  }
  

  IP anycast is a commonly used technique to share the load of a variety of global services. For more than one year, leveraging a lightweight technique for IP anycast detection, enumeration and geolocation, we perform regular IP monthly censuses. This paper provides a brief longitudinal study of the anycast ecosystem, and we additionally make all our datasets (raw measurements from PlanetLab and RIPE Atlas), results (monthly geolocated anycast replicas for all IP/24) and code available to the community.
• [TON-18] Araldo, Andrea and Dan, Gyorgy and Rossi, Dario, "Caching Encrypted Content via Stochastic Cache Partitioning" In IEEE/ACM Transactions on Networking, Vol. 26, 2018, DOI 10.1109/TNET.2018.2793892 Journal Abstract Bibtex

  @article{DR:TON-18,
    title = {Caching Encrypted Content via Stochastic Cache Partitioning},
    author = {Araldo, Andrea and Dan, Gyorgy and Rossi, Dario},
    year = {2018},
    volume = {26},
    issue = {1},
    doi = {10.1109/TNET.2018.2793892},
    journal = {IEEE/ACM Transactions on Networking},
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/rossi18ton.pdf}
  }
  

  In-network caching is an appealing solution to cope with the increasing bandwidth demand of video, audio and data transfer over the Internet. Nonetheless, in order to protect consumer privacy and their own business, Content Providers (CPs) increasingly deliver encrypted content, thereby preventing Internet Service Providers (ISPs) from employing traditional caching strategies, which require the knowledge of the objects being transmitted. To overcome this emerging tussle between security and effi- ciency, in this paper we propose an architecture in which the ISP partitions the cache space into slices, assigns each slice to a different CP, and lets the CPs remotely manage their slices. This architecture enables transparent caching of encrypted content, and can be deployed in the very edge of the ISP’s network (i.e., base stations, femtocells), while allowing CPs to maintain exclusive control over their content. We propose an algorithm, called SDCP, for partitioning the cache storage into slices so as to maximize the bandwidth savings provided by the cache. A distinctive feature of our algorithm is that ISPs only need to measure the aggregated miss rates of each CP, but they need not know of the individual objects that are requested. We prove that the SDCP algorithm converges to a partitioning that is close to the optimal, and we bound its optimality gap. We use simulations to evaluate SDCP’s convergence rate under stationary and non-stationary content popularity. Finally, we show that SDCP significantly outperforms traditional reactive caching techniques, considering both CPs with perfect and with imperfect knowledge of their content popularity.
• [IMC-17] Green, Thomas and Lambert, Anthony and Cristel, Pessler and Rossi, Dario., "Leveraging interdomain stability for squeezed and juicy BGP dynamics" ACM Internet Measurement Conference (IMC), Poster session nov. 2017, Conference Bibtex

  @inproceedings{DR:IMC-17,
    title = {Leveraging interdomain stability for squeezed and juicy BGP dynamics},
    author = {Green, Thomas and Lambert, Anthony and Cristel, Pessler and Rossi, Dario.},
    year = {2017},
    month = nov,
    booktitle = {ACM Internet Measurement Conference (IMC), Poster session}
  }
  
• [PARALLEL-CACHE-17] Tortelli, Michele and Rossi, Dario and Leonardi, Emilio, "Parallel Simulation of Very Large-Scale General Cache Networks" Telecom ParisTech nov. 2017, Tech.Rep. Bibtex

  @techrep{DR:PARALLEL-CACHE-17,
    title = {Parallel Simulation of Very Large-Scale General Cache Networks},
    author = {Tortelli, Michele and Rossi, Dario and Leonardi, Emilio},
    year = {2017},
    month = nov,
    institution = {Telecom ParisTech},
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/drossi17parallel-cache.pdf}
  }
  
• [IPID-17] Salutari, Flavia and Cicalese, Danilo and Rossi, Dario, "A closer look at IP-ID behavior in the Wild" Telecom ParisTech oct. 2017, Tech.Rep. Bibtex

  @techrep{DR:IPID-17,
    title = {A closer look at IP-ID behavior in the Wild},
    author = {Salutari, Flavia and Cicalese, Danilo and Rossi, Dario},
    institution = {Telecom ParisTech},
    month = oct,
    year = {2017},
    pages = {},
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/rossi17ipid.pdf}
  }
  
• [ATF-17] da Hora, Diego Neves and Asrese, Alemnew Sheferaw and Christophides, Vassilis and Teixeira, Renata and Rossi, Dario, "Narrowing the gap between QoS metrics and Web QoE using Above-the-fold metrics" Telecom ParisTech oct. 2017, Tech.Rep. Bibtex

  @techrep{DR:ATF-17,
    title = {Narrowing the gap between QoS metrics and Web QoE using Above-the-fold metrics},
    author = {da Hora, Diego Neves and Asrese, Alemnew Sheferaw and Christophides, Vassilis and Teixeira, Renata and Rossi, Dario},
    institution = {Telecom ParisTech},
    month = oct,
    year = {2017},
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/rossi17atf.pdf}
  }
  
• [TMM-17] Samain, Jacques and Carofiglio, Giovanna and Muscariello, Luca and Papalini, Michele and Sardara, Mauro and Tortelli, Michele and Rossi, Dario, "Dynamic Adaptive Video Streaming: Towards a systematic comparison of ICN and TCP/IP" In IEEE Transactions on Multimedia, Vol. 19, pp.2166-2181, oct. 2017, DOI 10.1109/TMM.2017.2733340 Journal Abstract Bibtex

  @article{DR:TMM-17,
    title = {Dynamic Adaptive Video Streaming: Towards a systematic comparison of ICN and TCP/IP},
    author = {Samain, Jacques and Carofiglio, Giovanna and Muscariello, Luca and Papalini, Michele and Sardara, Mauro and Tortelli, Michele and Rossi, Dario},
    journal = {IEEE Transactions on Multimedia},
    volume = {19},
    issue = {10},
    month = oct,
    year = {2017},
    doi = {10.1109/TMM.2017.2733340},
    pages = {2166-2181},
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/rossi17tmm.pdf}
  }
  

  Streaming of video contents over the Internet is experiencing an unprecedented growth. While video permeates every application, it also puts tremendous pressure in the network – to support users having heterogeneous accesses and expecting high quality of experience, in a furthermore cost-effective manner. In this context, Future Internet (FI) paradigms, such as Information Centric Networking (ICN), are particularly well suited to not only enhance video delivery at the client (as in the DASH approach), but to also naturally and seamlessly extend video support deeper in the network functions. In this paper, we contrast ICN and TCP/IP with an experimental approach, where we employ several state-of-the-art DASH controllers (PANDA, AdapTech, and BOLA) on an ICN vs TCP/IP network stack. Our campaign, based on tools which we developed and made available as open-source software, includes multiple clients (homogeneous vs heterogeneous mixture, synchronous vs asynchronous arrivals), videos (up to 4K resolution), channels (e.g., DASH profiles, emulated WiFi and LTE, real 3G/4G traces), and levels of integration with an ICN network (i.e., vanilla NDN, wireless loss detection and recovery at the access point, load balancing). Our results clearly illustrate, as well as quantitatively assess, benefits of ICN-based streaming, warning about potential pitfalls that are however easy to avoid.
• [COMNET-17a] Tortelli, Michele and Rossi, Dario and Leonardi, Emilio, "A Hybrid Methodology for the Performance Evaluation of Internet-scale Cache Networks" In Elsevier Computer Networks, Vol. 125, pp.146–159, sep. 2017, Journal Abstract Bibtex

  @article{DR:COMNET-17a,
    title = {A Hybrid Methodology for the Performance Evaluation of Internet-scale Cache Networks},
    author = {Tortelli, Michele and Rossi, Dario and Leonardi, Emilio},
    year = {2017},
    month = sep,
    journal = {Elsevier Computer Networks},
    pages = {146--159},
    volume = {125},
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/rossi17comnet-a.pdf}
  }
  

  Two concurrent factors challenge the evaluation of large-scale cache networks: complex algorithmic interactions, which are hardly represented by analytical models, and catalog/network size, which limits the scalability of event-driven simulations. To solve these limitations, we propose a new hybrid technique, that we colloquially refer to as ModelGraft, which combines elements of stochastic analysis within a simulative Monte-Carlo approach. In ModelGraft, large scenarios are mapped to a downscaled counterpart built upon Time-To-Live (TTL) caches, to achieve CPU and memory scalability. Additionally, a feedback loop ensures convergence to a consistent state, whose performance accurately represent those of the original system. Finally, the technique also retains simulation simplicity and flexibility, as it can be seamlessly applied to numerous forwarding, meta-caching, and replacement algorithms. We implement and make ModelGraft available as an alternative simulation engine of ccnSim. Performance evaluation shows that, with respect to classic event-driven simulation, ModelGraft gains over two orders of magnitude in both CPU time and memory complexity, while limiting accuracy loss below 2%. Ultimately, ModelGraft pushes the boundaries of the performance evaluation well beyond the limits achieved in the current state of the art, enabling the study of Internet-scale scenarios with content catalogs comprising hundreds billions objects.
• [COMNET-17b] Mansilha, R. and Barcellos, M. and Leonardi, E. and Rossi, D., "Exploiting Parallelism in Hierarchical Content Stores for High-speed ICN Routers" In Elsevier Computer Networks, Vol. 125, pp.132–145, sep. 2017, DOI 10.1016/j.comnet.2017.04.041 Journal Abstract Bibtex

  @article{DR:COMNET-17b,
    title = {Exploiting Parallelism in Hierarchical Content Stores for High-speed ICN Routers},
    author = {Mansilha, R. and Barcellos, M. and Leonardi, E. and Rossi, D.},
    journal = {Elsevier Computer Networks},
    month = sep,
    year = {2017},
    doi = {10.1016/j.comnet.2017.04.041},
    pages = {132--145},
    volume = {125},
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/rossi17comnet-b.pdf}
  }
  

  Information-centric network (ICN) is a novel architecture identifying data as a first class citizen, and caching as a prominent low-level feature. Yet, efficiently using large storage (e.g., 1 TB) at line rate (e.g., 10 Gbps) is not trivial: in our previous work, we proposed an ICN router design equipped with hierarchical caches, that exploits peculiarities of the ICN traffic arrival process. In this paper, we implement such proposal in the NDN Forwarding Daemon (NFD), and carry on a thorough experimental evaluation of its performance with an emulation methodology on common off the shelf hardware. Our study testifies the interest and feasibility of the approach.
• [LONGITUDINAL-17] Cicalese, Danilo and Rossi, Dario, "A longitudinal study of IP Anycast" Telecom ParisTech jul. 2017, Tech.Rep. Bibtex

  @techrep{DR:LONGITUDINAL-17,
    title = {A longitudinal study of IP Anycast},
    author = {Cicalese, Danilo and Rossi, Dario},
    institution = {Telecom ParisTech},
    month = jul,
    year = {2017},
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/rossi17longitudinal.pdf}
  }
  
• [PAM-17] Bocchi, Enrico and De Cicco, Luca and Mellia, Marco and Rossi, Dario, "The Web, the Users, and the MOS: Influence of HTTP/2 on User Experience" Passive and Active Measurements apr. 2017, Conference Abstract Bibtex

  @inproceedings{DR:PAM-17,
    title = {The Web, the Users, and the MOS: Influence of HTTP/2 on User Experience},
    author = {Bocchi, Enrico and De Cicco, Luca and Mellia, Marco and Rossi, Dario},
    year = {2017},
    month = apr,
    booktitle = {Passive and Active Measurements},
    halid = {hal-01613491},
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/rossi17pam.pdf}
  }
  

  This work focuses on the evaluation of Web quality of experience as perceived by actual users and in particular on the impact of HTTP/1 vs HTTP/2. We adopt an experimental methodology that uses real web pages served through a realistic testbed where we control network, protocol, and application configuration. Users are asked to browse such pages and provide their subjective feedback, which we leverage to obtain the Mean Opinion Score (MOS), while the testbed records objective metrics. The collected dataset comprises over 4,000 grades that we explore to tackle the question whether HTTP/2 improves users experience, to what extent, and in which conditions. Findings show that users report marginal differences, with 22%, 52%, 26% of HTTP/2 MOS being better, identical, or worse than HTTP/1, respectively. Even in scenarios that favor HTTP/2, results are not as sharp as expected. This is in contrast with objective metrics, which instead record a positive impact with HTTP/2 usage. This shows the complexity of understanding the web experience and the need to involve actual users in the quality assessment process.
• [COMMAG-17] Trevisan, Martino and Finamore, Alessandro and Mellia, Marco and Munafo, Maurizio and Rossi, Dario, "Traffic Analysis with Off-the-Shelf Hardware: Challenges and Lessons Learned" In IEEE Communication Magazine, Vol. 55, pp.163 - 169, mar. 2017, DOI 10.1109/MCOM.2017.1600756CM Journal Abstract Bibtex

  @article{DR:COMMAG-17,
    title = {{Traffic Analysis with Off-the-Shelf Hardware: Challenges and Lessons Learned}},
    author = {Trevisan, Martino and Finamore, Alessandro and Mellia, Marco and Munafo, Maurizio and Rossi, Dario},
    month = mar,
    year = {2017},
    journal = {IEEE Communication Magazine},
    volume = {55},
    issue = {3},
    doi = {10.1109/MCOM.2017.1600756CM},
    pages = {163 - 169},
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/rossi17commag.pdf}
  }
  

  In recent years, the progress in both hardware and software allows user-space applications to capture packets at 10 Gb/s line rate or more, with cheap COTS hardware. However, processing packets at such rates with software is still far from being trivial. In the literature, this challenge has been extensively studied for network intrusion detection systems, where per-packet operations are easy to parallelize with support of hardware acceleration. Conversely, the scalability of statistical traffic analyzers (STAs) is intrinsically complicated by the need to track per-flow state to collect statistics. This challenge has received less attention so far, and it is the focus of this work. We present and discuss design choices to enable a STA to collects hundreds of per-flow metrics at a multi-10-Gb/s line rate. We leverage a handful of hardware advancements proposed over the last years (e.g., RSS queues, NUMA architecture), and we provide insights on the trade-offs they imply when combined with state-of-the-art packet capture libraries and the multi-process paradigm. We outline the principles to design an optimized STA, and we implement them to engineer DPDKStat, a solution combining the Intel DPDK framework with the traffic analyzer Tstat. Using traces collected from real networks, we demonstrate that DPDKStat achieves 40 Gb/s of aggregated rate with a single COTS PC
• [ITC28a] Araldo, Andrea and Dan, Gyorgy and Rossi, Dario, "Stochastic Dynamic Cache Partitioning for Encrypted Content Delivery" ITC28, Runner-up for best paper award and receipient of the IEEE ComSoc/ISOC Internet Technical Committee Best paper award 2016-2017 sep. 2016, Conference Abstract Bibtex

  @inproceedings{DR:ITC28a,
    title = {Stochastic Dynamic Cache Partitioning for Encrypted Content Delivery},
    author = {Araldo, Andrea and Dan, Gyorgy and Rossi, Dario},
    year = {2016},
    month = sep,
    booktitle = {ITC28, Runner-up for best paper award and receipient of the IEEE ComSoc/ISOC Internet Technical Committee Best paper award 2016-2017},
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/rossi16itc28-a.pdf}
  }
  

  In-network caching is an appealing solution to cope with the increasing bandwidth demand of video, audio and data transfer over the Internet. Nonetheless, an increasing share of content delivery services adopt encryption through HTTPS, which is not compatible with traditional ISP-managed approaches like transparent and proxy caching. This raises the need for solutions involving both Internet Service Providers (ISP) and Content Providers (CP): by design, the solution should preserve business-critical CP information (e.g., content popularity, user preferences) on the one hand, while allowing for a deeper integration of caches in the ISP architecture (e.g., in 5G femto-cells) on the other hand. In this paper we address this issue by considering a contentoblivious ISP-operated cache. The ISP allocates the cache storage to various content providers so as to maximize the bandwidth savings provided by the cache: the main novelty lies in the fact that, to protect business-critical information, ISPs only need to measure the aggregated miss rates of the individual CPs and does not need to be aware of the objects that are requested, as in classic caching. We propose a cache allocation algorithm based on a perturbed stochastic subgradient method, and prove that the algorithm converges close to the allocation that maximizes the overall cache hit rate. We use extensive simulations to validate the algorithm and to assess its convergence rate under stationary and non-stationary content popularity. Our results (i) testify the feasibility of content-oblivious caches and (ii) show that the proposed algorithm can achieve within 10% from the global optimum in our evaluation.
• [ITC28b] Tortelli, Michele and Rossi, Dario and Leonardi, Emilio, "ModelGraft: Accurate, Scalable, and Flexible Performance Evaluation of General Cache Networks" ITC28 sep. 2016, Conference Abstract Bibtex

  @inproceedings{DR:ITC28b,
    title = {ModelGraft: Accurate, Scalable, and Flexible Performance Evaluation of General Cache Networks},
    author = {Tortelli, Michele and Rossi, Dario and Leonardi, Emilio},
    year = {2016},
    month = sep,
    booktitle = {ITC28},
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/rossi16itc28-b.pdf}
  }
  

  Large scale deployments of general cache networks, such as Content Delivery Networks or Information Centric Networking architectures, arise new challenges regarding their performance evaluation for network planning. On the one hand, analytical models can hardly represent in details all the interactions of complex replacement, replication, and routing policies on arbitrary topologies. On the other hand, the sheer size of networks and content catalogs makes event-driven simulation techniques inherently non-scalable. We propose a new technique for the performance evaluation of large-scale caching systems that intelligently integrates elements of stochastic analysis within a MonteCarlo simulative approach, that we colloquially refer to as ModelGraft. Our approach (i) leverages the intuition that complex scenarios can be mapped to a simpler equivalent scenario that builds upon Time-To-Live (TTL) caches; it (ii) significantly downscales the scenario to lower computation and memory complexity, while, at the same time, preserving its properties to limit accuracy loss; finally, it (iii) is simple to use and robust, as it autonomously converges to a consistent state through a feedback-loop control system, regardless of the initial state. Performance evaluation shows that, with respect to classic event-driven simulation, ModelGraft gains over two orders of magnitude in both CPU time and memory complexity, while limiting accuracy loss below 2%. In addition, we show that ModelGraft extends performance evaluation well beyond the boundaries of classic approaches, by enabling study of Internet-scale scenarios with content catalogs comprising hundreds of billions objects.
• [TOMPECS-16] De Cicco, Luca and Gong, Yixi and Rossi, Dario and Leonardi, Emilio, "A control theoretic analysis of low-priority congestion control reprioritization under AQM" In ACM Transactions on Modeling and Performance Evaluation of Computer Systems, Vol. 1, pp.17:1–17:33, sep. 2016, Journal Abstract Bibtex

  @article{DR:TOMPECS-16,
    title = {A control theoretic analysis of low-priority congestion control reprioritization under AQM},
    author = {De Cicco, Luca and Gong, Yixi and Rossi, Dario and Leonardi, Emilio},
    year = {2016},
    month = sep,
    journal = {ACM Transactions on Modeling and Performance Evaluation of Computer Systems},
    volume = {1},
    issue = {4},
    pages = {17:1--17:33},
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/rossi16tompecs.pdf}
  }
  

  Recently, a negative interplay has been shown to arise when scheduling/Active Queue Management (AQM) techniques and low-priority congestion control protocols are used together; namely, AQM resets the relative level of priority among congestion control protocols. This work explores this issue by carrying out a control-theoretic analysis of the dynamical system to prove some fundamental properties that fully characterize the reprioritization phenomenon. In particular, (i) we provide the closed-form solution of the equilibrium in the open loop (i.e., fixing a target loss probability p); (ii) we provide a stability analysis and a characterization of the reprioritization phenomenon when closing the loop with AQM (i.e., that dynamically adjusts the system loss probability). Our results are important as the characterization of the reprioritization phenomenon is not only quantitatively accurate for the specific protocols and AQM considered but also qualitatively accurate for a broader range of congestion control protocol and AQM combinations. Finally, while we find a sufficient condition to avoid the reprioritization phenomenon, we also show, at the same time, such conditions to be likely impractical: Therefore, we propose a simple and practical system-level solution that is able to reinstate priorities among protocols.
• [ICN-16a] Tortelli, M. and Rossi, D. and Leonardi, E., "Running ModelGraft to Evaluate Internet-scale ICN" ACM ICN, Demo session sep. 2016, Conference Abstract Bibtex

  @inproceedings{DR:ICN-16a,
    author = {Tortelli, M. and Rossi, D. and Leonardi, E.},
    title = {Running ModelGraft to Evaluate Internet-scale ICN},
    booktitle = {ACM ICN, Demo session},
    address = {Kyoto, Japan},
    year = {2016},
    month = sep,
    pages = {213--214},
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/MISSINGURL.pdf}
  }
  

  The analysis of Internet-scale Information-centric networks, and of cache networks in general, poses scalability issues like CPU and memory requirements, which can not be easily targeted by neither state-of-the-art analytical models nor well designed event-driven simulators. This demo focuses on showcasing performance of our new hybrid methodology, named ModelGraft, which we release as a simulation engine of the open-source ccnSim simulator: being able to seamlessly use a classic event-driven or the novel hybrid engine dramatically improves the flexibility and scalability of current simulative and analytical tools. In particular, ModelGraft combines elements and intuitions of stochastic analysis into a MonteCarlo simulative approach, offering a reduction of over two orders of magnitude in both CPU time and memory occupancy, with respect to the purely event-driven version of ccnSim, notably one of the most scalable simulators for Information-centric networks. This demo consists in gamifying the aforementioned comparison: we represent ModelGraft vs event-driven simulation as two athletes running a 100-meter competition using sprite-based animations. Differences between the two approaches in terms of CPU time, memory occupancy, and results accuracy, are highlighted in the score-board.
• [ICN-16b] Enguehard, M. and Droms, R. and Rossi, D., "On the Cost of Secure Association of Information Centric Things" ACM ICN, Poster session sep. 2016, Conference Abstract Bibtex

  @inproceedings{DR:ICN-16b,
    author = {Enguehard, M. and Droms, R. and Rossi, D.},
    title = {On the Cost of Secure Association of Information Centric Things},
    booktitle = {ACM ICN, Poster session},
    address = {Kyoto, Japan},
    year = {2016},
    month = sep,
    pages = {207--208},
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/MISSINGURL.pdf}
  }
  

  Information Centric Networking (ICN) paradigms nicely fit the world of wireless sensors, whose devices have tight constraints. In this poster, we compare two alternative designs for secure association of new IoT devices in existing ICN deployments, which are based on asymmetric and symmetric cryptography respectively. While the security properties of both approaches are equivalent, an interesting trade-off arises between properties of the protocol vs properties of its implementation in current IoT boards. Indeed, while the asymmetric-keys based approach incurs a lower traffic overhead (of about 30%), we find that its implementation is significantly more energy- and time-consuming due to the cost of cryptographic operations (it requires up to 41x more energy and 8x more time).
• [ICN-16c] Enguehard, M. and Droms, R. and Rossi, D., "SLICT: Secure Localized Information Centric Things" ACM ICN, IC5G workshop sep. 2016, Conference Abstract Bibtex

  @inproceedings{DR:ICN-16c,
    author = {Enguehard, M. and Droms, R. and Rossi, D.},
    title = {SLICT: Secure Localized Information Centric Things},
    booktitle = {ACM ICN, IC5G workshop},
    address = {Kyoto, Japan},
    year = {2016},
    month = sep,
    pages = {255--260},
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/MISSINGURL.pdf}
  }
  

  While the potential advantages of geographic forwarding in wireless sensor networks (WSN) have been demonstrated for a while now, research in applying Information Centric Networking (ICN) has only gained momentum in the last few years. In this paper, we bridge these two worlds by proposing an ICN-compliant and secure implementation of geographic forwarding for ICN. We implement as a proof of concept the Greedy Perimeter Stateless Routing (GPSR) algorithm and compare its performance to that of vanilla ICN forwarding. We also evaluate the cost of security in 802.15.4 networks in terms of energy, memory and CPU footprint. We show that in sparse but large networks, GPSR outperforms vanilla ICN forwarding in both memory footprint and CPU consumption. However, GPSR is more energy intensive because of the cost of communications.
• [SIGCOMM-QoE-16] Bocchi, Enrico and De Cicco, Luca and Rossi, Dario, "Measuring the Quality of Experience of Web users" ACM SIGCOMM Workshop on QoE-based Analysis and Management of Data Communication Networks (Internet-QoE 2016), selected as best paper in the workshop for reprint in ACM SIGCOMM Comput. Commun. Rev. aug. 2016, Conference Bibtex

  @inproceedings{DR:SIGCOMM-QoE-16,
    title = {Measuring the Quality of Experience of Web users},
    author = {Bocchi, Enrico and De Cicco, Luca and Rossi, Dario},
    year = {2016},
    month = aug,
    booktitle = {ACM SIGCOMM Workshop on QoE-based Analysis and Management of Data Communication Networks (Internet-QoE 2016), selected as best paper in the workshop for reprint in ACM SIGCOMM Comput. Commun. Rev.},
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/rossi16internet-qoe.pdf}
  }
  
• [COMNET-16b] Bocchi, Enrico and Safari Khatouni, Ali and Traverso, Stefano and Finamore, Alessandro and Munafo, Maurizio and Mellia, Marco and Rossi, Dario, "Statistical Network Monitoring: Methodology and Application to Carrier-Grade NAT" In Elsevier Computer Networks, Vol. 107, jun. 2016, Journal Abstract Bibtex

  @article{DR:COMNET-16b,
    title = {Statistical Network Monitoring: Methodology and Application to Carrier-Grade NAT},
    author = {Bocchi, Enrico and Safari Khatouni, Ali and Traverso, Stefano and Finamore, Alessandro and Munafo, Maurizio and Mellia, Marco and Rossi, Dario},
    volume = {107},
    month = jun,
    year = {2016},
    journal = {Elsevier Computer Networks},
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/MISSINGURL.pdf}
  }
  

  When considering to passively collect and then process network traffic traces, the need to analyze raw data at several Gbps and to extract higher level indexes from the stream of packets poses typical BigData-like challenges. In this paper, we engineer a methodology to extract, collect and process passive traffic traces. In particular, we design and implement analytics that, based on a filtering process and on the building of empirical distributions, enable the comparison between two generic collections, e.g., data gathered from two different vantage points, from different populations, or at different times. The ultimate goal is to highlight statistically significant differences that could be useful to flag to incidents for the network manager. After introducing the methodology, we apply it to assess the impact of Carrier-Grade NAT (CGN), a technology that Internet Service Providers (ISPs) deploy to limit the usage of expensive public IP addresses. Since CGN may introduce connectivity issues and performance degradation, we process a large dataset of passive measurements collected from an ISP using CGN for part of its customers. We first extract detailed per-flow information by processing packets from live links. Then, we derive higher level statistics that are significant for the end-users, e.g., TCP connection setup time, HTTP response time, or BitTorrent average download throughput. At last, we contrast figures of customers being offered public or private addresses, and look for statistically significant differences. Results show that CGN does not impair quality of service in the analyzed ISP deployment. In addition, we use the collected data to derive useful figures for the proper dimensioning of the CGN and the configuration of its parameters in order to avoid impairments on end-users experience
• [NETWORKING-16] Araldo, Andrea and Martignon, Fabio and Rossi, Dario, "Representation Selection Problem: Optimizing Video Delivery through Caching" IFIP Networking may. 2016, Conference Abstract Bibtex

  @inproceedings{DR:NETWORKING-16,
    title = {Representation Selection Problem: Optimizing Video Delivery through Caching},
    author = {Araldo, Andrea and Martignon, Fabio and Rossi, Dario},
    year = {2016},
    month = may,
    booktitle = {IFIP Networking},
    pages = {323-331},
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/rossi16networking.pdf}
  }
  

  To cope with Internet video explosion, recent work proposes to deploy caches to absorb part of the traffic related to popular videos. Nonetheless, caching literature has mainly focused on network-centric metrics, while the quality of users’ video streaming experience should be the key performance index to optimize. Additionally, the general assumption is that each user request can be satisfied by a single object, which does not hold when multiple representations at different quality levels are available for the same video. Our contribution in this paper is to extend the classic object placement problem (which object to cache and where) by further considering the representation selection problem (i.e., which quality representation to cache), employing two methodologies to tackle this challenge. First, we employ a Mixed Integer Linear Programming (MILP) formulation to obtain the centralized optimal solution, as well as bounds to natural policies that are readily obtained as additional constraints of the MILP. Second, from the structure of the optimal solution, we learn guidelines that assist the design of distributed caching strategies: namely, we devise a simple yet effective distributed strategy that incrementally improves the quality of cached objects. Via simulation over large scale scenarios comprising up to hundred nodes and hundred million objects, we show our proposal to be effective in balancing user perceived utility vs bandwidth usage.
• [INFOCOM-IC-16] Bocchi, Enrico and De Cicco, Luca and Rossi, Dario, "Web QoE: Moving beyond Google’s SpeedIndex" Finalist at the IEEE INFOCOM Innovation Challenge, apr. 2016, Conference Bibtex

  @inproceedings{DR:INFOCOM-IC-16,
    title = {Web QoE: Moving beyond Google's SpeedIndex},
    author = {Bocchi, Enrico and De Cicco, Luca and Rossi, Dario},
    year = {2016},
    month = apr,
    booktitle = {Finalist at the IEEE INFOCOM Innovation Challenge,},
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/rossi16infocom-innovation-challenge.pdf}
  }
  
• [DIRECTORSCUT-16] Bocchi, Enrico and De Cicco, Luca and Mellia, Marco and Rossi, Dario, "HTTP/2 vs the Users: The Good, The Bad and The Ugly (Director’s Cut)" Technical Report apr. 2016, Conference Bibtex

  @inproceedings{DR:DIRECTORSCUT-16,
    title = {HTTP/2 vs the Users: The Good, The Bad and The Ugly (Director's Cut)},
    author = {Bocchi, Enrico and De Cicco, Luca and Mellia, Marco and Rossi, Dario},
    year = {2016},
    month = apr,
    booktitle = {Technical Report},
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/director.pdf}
  }
  
• [CCN-TR16] Tortelli, Michele and Rossi, Dario and Leonardi, Emilio, "Model-Graft: Accurate, Scalable and Flexible Analysis of General Cache Networks" Tech. Rep. 2016, Conference Bibtex

  @inproceedings{DR:CCN-TR16,
    title = {Model-Graft: Accurate, Scalable and Flexible Analysis of General Cache Networks},
    author = {Tortelli, Michele and Rossi, Dario and Leonardi, Emilio},
    year = {2016},
    booktitle = {Tech. Rep.},
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/ModelGraft.pdf}
  }
  
• [P2P-15] Schaub, Alexander and Rossi, Dario, "Design and Analysis of an Improved BitMessage Anti-spam Mechanism" IEEE P2P’XIV sep. 2015, Conference Abstract Bibtex

  @inproceedings{DR:P2P-15,
    title = {Design and Analysis of an Improved BitMessage Anti-spam Mechanism},
    author = {Schaub, Alexander and Rossi, Dario},
    year = {2015},
    booktitle = {IEEE P2P'XIV},
    month = sep,
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/rossi15p2p.pdf}
  }
  

  The BitMessage protocol offers privacy to its anonymous users. It is a completely decentralized messaging system, enabling users to exchange messages preventing accidental eavesdropping – a nice features in the Post-Snowden Internet Era. Not only messages are sent to every node on the network (making it impossible to understand the intended recipient), but their content is encrypted with the intended recipient public key (so that s/he only can decipher it). As these two properties combined might facilitate spamming, a proof-of-work (PoW) mechanism has been designed to mitigate this threat: only messages exhibiting properties of the PoW are forwarded on the network: since PoW is based on computationally heavy cryptographic functions, this slows down the rate at which spammers can introduce unsolicited messages in the network on the one hand, but also makes it harder to send legitimate messages for regular users on the other hand. In this paper, we (i) carry on an analysis of the current PoW mechanism, (ii) propose a very simple, yet very effective, generalization of the formula that decouples spammers vs legitimate users penalty showing that (iii) at the optimum, our proposal halves the harm spammers can do, avoiding by definition any impact for legitimate users.
• [ICN-15] R. Mansilha, L. Saino, M. Barcellos, M. Gallo, E. Leonardi, D. Perino and D. Rossi, "Hierarchical Content Stores in High-speed ICN Routers: Emulation and Prototype Implementation" ACM SIGCOMM Conference on Information-Centric Networking (ICN’15) sep. 2015, Conference Abstract Bibtex

  @inproceedings{DR:ICN-15,
    title = {Hierarchical Content Stores in High-speed ICN Routers: Emulation and Prototype Implementation},
    author = {{R. Mansilha, L. Saino, M. Barcellos, M. Gallo, E. Leonardi, D. Perino and D. Rossi}},
    booktitle = {ACM SIGCOMM Conference on Information-Centric Networking (ICN'15)},
    address = {San Francisco, CA},
    month = sep,
    year = {2015},
    pages = {147-156},
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/rossi15icn.pdf}
  }
  

  Recent work motivates the design of Information-centric rou-ters that make use of hierarchies of memory to jointly scale in the size and speed of content stores. The present paper advances this understanding by (i) instantiating a general purpose two-layer packet-level caching system, (ii) investigating the solution design space via emulation, and (iii) introducing a proof-of-concept prototype. The emulation-based study reveals insights about the broad design space, the expected impact of workload, and gains due to multi-threaded execution. The full-blown system prototype experimentally confirms that, by exploiting both DRAM and SSD memory technologies, ICN routers can sustain cache operations in excess of 10Gbps running on off-the-shelf hardware.
• [ICC-15] Spina, Michele and Rossi, Dario and Sozio, Mauro and Maniu, Silviu and Cautis, Bogdan, "Snooping Wikipedia Vandals with MapReduce" IEEE ICC jun. 2015, Conference Abstract Bibtex

  @inproceedings{DR:ICC-15,
    title = {Snooping Wikipedia Vandals with MapReduce},
    author = {Spina, Michele and Rossi, Dario and Sozio, Mauro and Maniu, Silviu and Cautis, Bogdan},
    year = {2015},
    booktitle = {IEEE ICC},
    month = jun,
    address = {London, UK},
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/rossi15icc.pdf}
  }
  

  In this paper, we present and validate an algorithm able to accurately identify anomalous behaviors on online and collaborative social networks, based on their interaction with other fellows. We focus on Wikipedia, where accurate ground truth for the classification of vandals can be reliably gathered by manual inspection of the page edit history. We develop a distributed crawler and classifier tasks, both implemented in MapReduce, with whom we are able to explore a very large dataset, consisting of over 5 millions articles collaboratively edited by 14 millions authors, resulting in over 8 billion pairwise interactions. We represent Wikipedia as a signed network, where positive arcs imply constructive interaction between editors. We then isolate a set of high reputation editors (i.e., nodes having many positive incoming links) and classify the remaining ones based on their interactions with high reputation editors. We demonstrate our approach not only to be practically relevant (due to the size of our dataset), but also feasible (as it requires few MapReduce iteration) and accurate (over 95% true positive rate). At the same time, we are able to classify only about half of the dataset editors (recall of 50%) for which we outline some solution under study.
• [TMA-15] Espinet, Francois and Joumblatt, Diana and Rossi, Dario, "Zen and the art of network troubleshooting: a hands on experimental study" Traffic Monitoring and Analysis (TMA’15) apr. 2015, Conference Abstract Bibtex

  @inproceedings{DR:TMA-15,
    title = {Zen and the art of network troubleshooting: a hands on experimental study},
    author = {Espinet, Francois and Joumblatt, Diana and Rossi, Dario},
    year = {2015},
    booktitle = {Traffic Monitoring and Analysis (TMA'15)},
    month = apr,
    address = {Barcellona, Spain},
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/MISSINGURL.pdf}
  }
  

  Growing network complexity necessitates tools and methodologies to automate network troubleshooting. In this paper, we follow a crowd-sourcing trend, and argue for the need to deploy measurement probes at end-user devices and gateways, which can be under the control of the users or the ISP. Depending on the amount of information available to the probes (e.g., ISP topology), we formalize the network troubleshooting task as either a clustering or a classification problem, that we solve with an algorithm that (i) achieves perfect classification under the assumption of a strategic selection of probes (e.g., assisted by an ISP) and (ii) operates blindly with respect to the network performance metrics, of which we consider delay and bandwidth in this paper. While previous work on network troubleshooting privileges a more theoretical vs practical approaches, our workflow balances both aspects as (i) we conduct a set of controlled experiments with a rigorous and reproducible methodology, (ii) on an emulator that we thoroughly calibrate, (iii) contrasting experimental results affected by real-world noise with expected results from a probabilistic model.
• [DRCN-15] Mazloum, Riad and Auge, Jordan and Rossi, Dario and Friedman, Timur, "Errors Announcing 32-bit ASNs in BGP Routes" 11th International Conference on Design of Reliable Communication Networks (DRCN’15), Extended Abstract mar. 2015, Conference Abstract Bibtex

  @inproceedings{DR:DRCN-15,
    title = {Errors Announcing 32-bit ASNs in BGP Routes},
    author = {Mazloum, Riad and Auge, Jordan and Rossi, Dario and Friedman, Timur},
    year = {2015},
    booktitle = {11th International Conference on Design of Reliable Communication Networks (DRCN'15), Extended Abstract},
    month = mar,
    address = {Kansas City, USA},
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/rossi15drcn.pdf}
  }
  

  We present evidence of a phenomenon where there is large scale misconfigurations of BGP routers starting in 2007 and continuing to the present date. This has to do with the change from 16-bit to 32-bit autonomous system (AS) numbering and the employment of the fictitious AS, AS23456. This error strongly biases estimations of the number of ASes performing a type of inter-domain routing called multi-exit routing. In data from 2010, over half of apparent cases are in fact false. We show how to detect this error and obtain a truer picture of the extent of multi-exit routing.
• [TPDPS-15] Araldo, A. and Rossi, D. and Martignon, F., "Cost-aware caching: Caching more (costly items) for less (ISPs operational expenditures)" In IEEE Transactions on Parallel and Distributed Systems, Vol. to appear, . 2015, DOI 10.1109/TPDS.2015.2433296 Journal Abstract Bibtex

  @article{DR:TPDPS-15,
    author = {Araldo, A. and Rossi, D. and Martignon, F.},
    journal = {IEEE Transactions on Parallel and Distributed Systems},
    title = {Cost-aware caching: Caching more (costly items) for less (ISPs operational expenditures)},
    year = {2015},
    month = {},
    volume = {to appear},
    keywords = {Approximation methods;Catalogs;Computational modeling;Economics;Internet;Load modeling;Proposals},
    doi = {10.1109/TPDS.2015.2433296},
    issn = {1045-9219},
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/rossi15tpdps.pdf}
  }
  

  Albeit an important goal of caching is traffic reduction, a perhaps even more important aspect follows from the above achievement: the reduction of Internet Service Provider (ISP) operational costs that comes as a consequence of the reduced load on transit and provider links. Surprisingly, to date this crucial aspect has not been properly taken into account in cache design. In this paper, we show that the classic caching efficiency indicator, i.e. the hit ratio, conflicts with cost. We therefore propose a mechanism whose goal is the reduction of cost and, in particular, we design a Cost-Aware (CoA) cache decision policy that, leveraging price heterogeneity among external links, tends to store with more probability the objects that the ISP has to retrieve through the most expensive links. We provide a model of our mechanism, based on Che’s approximation, and, by means of a thorough simulation campaign, we contrast it with traditional cost-blind schemes, showing that CoA yields a significant cost saving, that is furthermore consistent over a wide range of scenarios. We show that CoA is easy to implement and robust, making the proposal of practical relevance.
• [GLOBECOM-14] , "Cost-aware caching: optimizing cache provisioning and object placement in ICN" IEEE Globecom dec. 2014, Conference Abstract Bibtex

  @inproceedings{DR:GLOBECOM-14,
    author = {},
    title = {Cost-aware caching: optimizing cache provisioning and object placement in ICN},
    booktitle = {IEEE Globecom},
    address = {Austin, Texas},
    month = dec,
    year = {2014},
    pages = {1108 - 1113},
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/rossi14globecom.pdf}
  }
  

  Caching is frequently used by Internet Service Providers as a viable technique to reduce the latency perceived by end users, while jointly offloading network traffic. While the cache hit-ratio is generally considered in the literature as the dominant performance metric for such type of systems, in this paper we argue that a critical missing piece has so far been neglected. Adopting a radically different perspective, in this paper we explicitly account for the cost of content retrieval, i.e. the cost associated to the external bandwidth needed by an ISP to retrieve the contents requested by its customers. Interestingly, we discover that classical cache provisioning techniques that maximize cache efficiency (i.e., the hit-ratio), lead to suboptimal solutions with higher overall cost. To show this mismatch, we propose two optimization models that either minimize the overall costs or maximize the hit-ratio, jointly providing cache sizing, object placement and path selection. We formulate a polynomial- time greedy algorithm to solve the two problems and analytically prove its optimality. We provide numerical results and show that significant cost savings are attainable via a cost-aware design.
• [ICN-14a] Araldo, Andrea and Rossi, Dario and Martignon, Fabio, "Design and Evaluation of Cost-aware Information Centric Routers" 1st ACM SIGCOMM Conference on Information-Centric Networking (ICN-2014) sep. 2014, Conference Abstract Bibtex

  @inproceedings{DR:ICN-14a,
    title = {Design and Evaluation of Cost-aware Information Centric Routers},
    author = {Araldo, Andrea and Rossi, Dario and Martignon, Fabio},
    booktitle = {1st ACM SIGCOMM Conference on Information-Centric Networking (ICN-2014)},
    address = {Paris, France},
    month = sep,
    year = {2014},
    pages = {147-156},
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/rossi14icn-a.pdf}
  }
  

  Albeit an important goal of Information Centric Networking (ICNs) is traffic reduction, a perhaps even more important aspect follows from the above achievement: the reduction of ISP operational costs that comes as consequence of the reduced load on transit and provider links. Surprisingly, to date this crucial aspect has not been properly taken into account, neither in the architectural design, nor in the op- eration and management of ICN proposals. In this work, we instead design a distributed cost-aware scheme that explicitly considers the cost heterogeneity among different links. We contrast our scheme with both traditional cost-blind schemes and optimal results. We further propose an architectural design to let multiple schemes be interoper- able, and finally assess whether overlooking implementation details could hamper the practical relevance of our design. Numerical results show that our cost-aware scheme can yield significant cost savings, that are furthermore consistent over a wide range of scenarios.
• [ICN-14b] Rossini, Giuseppe and Rossi, Dario, "Coupling caching and forwarding: Benefits, analysis, and implementation" 1st ACM SIGCOMM Conference on Information-Centric Networking (ICN-2014) sep. 2014, Conference Abstract Bibtex

  @inproceedings{DR:ICN-14b,
    title = {Coupling caching and forwarding: Benefits, analysis, and implementation},
    author = {Rossini, Giuseppe and Rossi, Dario},
    booktitle = {1st ACM SIGCOMM Conference on Information-Centric Networking (ICN-2014)},
    address = {Paris, France},
    month = sep,
    year = {2014},
    pages = {127-136},
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/rossi14icn-b.pdf}
  }
  

  A recent debate revolves around the usefulness of pervasive caching, i.e., adding caching capabilities to possibly every router of the future Internet. Recent research argues against it, on the ground that it provides only very limited gain with respect to the current CDN scenario, where caching only happens at the network edge. In this paper, we instead show that advantages of ubiquitous caching appear only when meta-caching (i.e., whether or not cache the incoming object) and forwarding (i.e., where to direct requests in case of cache miss) decisions are tightly coupled. Summarizing our contributions, we (i) show that gains can be obtained provided that ideal Nearest Replica Routing (iNRR) forwarding and Leave a Copy Down (LCD) meta-caching are jointly in use, (ii) model the iNRR forwarding policy, (iii) provide two alternative implementations that arbitrarily closely approximate iNRR behavior, and (iv) promote cross-comparison by making our code available to the community.
• [ICN-14d] Imbrenda, Claudio and Muscariello, Luca and Rossi, Dario, "Analyzing Cacheability in the Access Network with HACkSAw" 1st ACM SIGCOMM Conference on Information-Centric Networking (ICN-2014), Demo Session sep. 2014, Conference Abstract Bibtex

  @inproceedings{DR:ICN-14d,
    title = {Analyzing Cacheability in the Access Network with HACkSAw},
    author = {Imbrenda, Claudio and Muscariello, Luca and Rossi, Dario},
    booktitle = {1st ACM SIGCOMM Conference on Information-Centric Networking (ICN-2014), Demo Session},
    address = {Paris, France},
    month = sep,
    year = {2014},
    pages = {201-202},
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/rossi14icn-d.pdf}
  }
  

  Web traffic is growing, and the need for accurate traces of HTTP traffic is therefore also rising, both for operators and researchers, as accurate HTTP traffic traces allow to analyse and characterize the traffic and the clients, and to analyse the performance of the network and the perceived quality of service for the final users. Since most ICN proposals also advocate for pervasive caching, it is imperative to measure the cacheability of traffic to assess the impact and/or the potential benefits of such solutions. This demonstration will show a both a tool to collect HTTP traces that is both fast and accurate and that overcomes the limitations of existing tools, and a set of important statistics that can be computed in post processing, like aggregate/demultiplexed cacheability figures.
• [ICN-14e] Tortelli, Michele and Rossi, Dario and Boggia, Gennaro and Grieco, Luigi Alfredo, "CCN Simulators: Analysis and Cross-Comparison" 1st ACM SIGCOMM Conference on Information-Centric Networking (ICN-2014), Demo Session sep. 2014, Conference Bibtex

  @inproceedings{DR:ICN-14e,
    title = {CCN Simulators: Analysis and Cross-Comparison},
    author = {Tortelli, Michele and Rossi, Dario and Boggia, Gennaro and Grieco, Luigi Alfredo},
    booktitle = {1st ACM SIGCOMM Conference on Information-Centric Networking (ICN-2014), Demo Session},
    address = {Paris, France},
    month = sep,
    year = {2014},
    pages = {197-198},
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/rossi14icn-e.pdf}
  }
  
• [QICN-14] Tortelli, Michele and Rossi, Dario and Boggia, Gennaro and Grieco, Luigi Alfredo, "Pedestrian Crossing: The Long and Winding Road toward Fair Cross-comparison of ICN Quality" International Workshop on Quality, Reliability, and Security in Information-Centric Networking (Q-ICN) aug. 2014, Conference Abstract Bibtex

  @inproceedings{DR:QICN-14,
    title = {Pedestrian Crossing: The Long and Winding Road toward Fair Cross-comparison of ICN Quality},
    author = {Tortelli, Michele and Rossi, Dario and Boggia, Gennaro and Grieco, Luigi Alfredo},
    booktitle = {International Workshop on Quality, Reliability, and Security in Information-Centric Networking (Q-ICN)},
    address = {Rhodes, Greece},
    month = aug,
    year = {2014},
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/rossi14qicn.pdf}
  }
  

  While numerous Information Centric Networking (ICN) architectures have been proposed over the last years, the community has so far only timidly attempted at a quantitative assessment of the relative quality of service level that users are expected to enjoy in each of them. This paper starts a journey toward the cross comparison of ICN alternatives, making several contributions along this road. Specifically, a census of 20 ICN software tools reveals that about 10 are dedicated to a specific architecture, about half of which are simulators. Second, we survey ICN research papers using simulation to gather information concerning the used simulator, finding that a large fraction either uses custom proprietary and unavailable software, or even plainly fails to mention any information on this regard, which is deceiving. Third, we cross-compare some of the available simulators, finding that they achieve consistent results, which is instead encouraging. Fourth, we propose a methodology to increase and promote cross- comparison, which is within reach but requires community-wide agreement, promotion and enforcement.
• [INFOCOM-14] Rossini, G. and Rossi, D. and Garetto, G. and Leonardi, E., "Multi-Terabyte and Multi-Gbps Information Centric Routers" IEEE INFOCOM apr. 2014, Conference Abstract Bibtex

  @inproceedings{DR:INFOCOM-14,
    title = {Multi-Terabyte and Multi-Gbps Information Centric Routers},
    author = {Rossini, G. and Rossi, D. and Garetto, G. and Leonardi, E.},
    year = {2014},
    booktitle = {IEEE INFOCOM},
    month = apr,
    address = {Toronto, Canada},
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/MISSINGURL.pdf}
  }
  

  One of the main research directions along which the future Internet is evolving can be identified in the paradigmatic shift from a network of hosts toward a network of caches. Yet, several questions remain concerning the scalability of individual algorithms (e.g., name based lookup and routing) and components (e.g., caches) of these novel Information Centric Networking (ICN) architectures. Exploiting a peculiar characteristics of ICN (i.e., the fact that contents are split in chunks), and the nature of video streaming (which dominates Internet traffic), this paper proposes a novel two-layers caching scheme that allows multi-Terabyte caches to sustain content streaming at multi-Gbps speed. We model the system as an extension, to the case of chunked contents, of the well known Che approximation, that has the advantage of being very simple and accurate at the same time. Simulations under synthetic and realistic trace-driven traffic confirm the accuracy of the analysis and the feasibility of the proposed architecture.
• [PAM-14a] Colabrese, S. and Rossi, D. and Mellia, M., "Scalable accurate consolidation of passively measured statistical data" Passive and Active Measurement (PAM), Extended Abstract mar. 2014, Conference Abstract Bibtex

  @inproceedings{DR:PAM-14a,
    author = {Colabrese, S. and Rossi, D. and Mellia, M.},
    title = {Scalable accurate consolidation of passively measured statistical data},
    booktitle = {Passive and Active Measurement (PAM), Extended Abstract},
    year = {2014},
    address = {Los Angeles, USA},
    month = mar,
    pages = {262--264},
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/MISSINGURL.pdf}
  }
  

  Passive probes continuously collect a significant amount of traffic volume, and autonomously generate statistics on a large number of metrics. A common statistical output of passive probe is represented by probability mass functions (pmf). The need for consolidation of several pmfs arises in two contexts, namely: (i) whenever a central point collects and aggregates measurement of multiple disjoint vantage points, and (ii) whenever a local measurement processed at a single vantage point needs to be distributed over multiple cores of the same physical probe, in order to cope with growing link capacity. Taking an experimental approach, we study both cases assessing the impact of different consolidation strategies, obtaining general design and tuning guidelines.
• [AINTEC-2014] Rossi, D., "Anycast enumeration and geolocation" Keynote speech at ACM SIGCOMM AINTEC’2014 2014, Tech.Rep. Bibtex

  @techreport{DR:AINTEC-2014,
    title = {Anycast enumeration and geolocation},
    author = {Rossi, D.},
    institution = {Keynote speech at ACM SIGCOMM AINTEC'2014},
    year = {2014},
    date = {November},
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/rossi14aintec.pptx}
  }
  
• [PATENT-08] Rossi, D. and Rossini, G., "Method for managing packets in a network of Information Centric Networking (ICN) nodes" , https://perso.telecom-paristech.fr/drossi/paper/MISSINGURL.pdf 2014, Patent

  @misc{DR:PATENT-08,
    author = {Rossi, D. and Rossini, G.},
    title = {Method for managing packets in a network of Information Centric Networking (ICN) nodes},
    year = {2014},
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/MISSINGURL.pdf}
  }
  
• [PATENT-07] Rossini, Giuseppe and Rossi, Dario and Garetto, Michele and Leonardi, Emilio, "Information Centric Networking (ICN) router" , https://perso.telecom-paristech.fr/drossi/paper/MISSINGURL.pdf 2014, Patent

  @misc{DR:PATENT-07,
    author = {Rossini, Giuseppe and Rossi, Dario and Garetto, Michele and Leonardi, Emilio},
    title = {Information Centric Networking (ICN) router},
    year = {2014},
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/MISSINGURL.pdf}
  }
  
• [PATENT-09] Rossi, D. and Rossini, G., "Method for managing packets in a network of Information Centric Networking (ICN) nodes" , Patent EPO14305866.7 2014, Patent

  @misc{DR:PATENT-09,
    author = {Rossi, D. and Rossini, G.},
    howpublished = {Patent EPO14305866.7},
    title = {Method for managing packets in a network of Information Centric Networking (ICN) nodes},
    year = {2014}
  }
  
• [PATENT-10] Rossini, Giuseppe and Rossi, Dario and Garetto, Michele and Leonardi, Emilio, "Information Centric Networking (ICN) router" , Patent EPO14305639.8 2014, Patent

  @misc{DR:PATENT-10,
    author = {Rossini, Giuseppe and Rossi, Dario and Garetto, Michele and Leonardi, Emilio},
    howpublished = {Patent EPO14305639.8},
    title = {Information Centric Networking (ICN) router},
    year = {2014}
  }
  
• [COMNET-13] , "Rethinking low extra delay backtround transport protocols" In Elsevier Computer Networks, Vol. 57, pp.1838–1852, jun. 2013, Journal Abstract Bibtex

  @article{DR:COMNET-13,
    title = {Rethinking low extra delay backtround transport protocols},
    author = {},
    journal = {Elsevier Computer Networks},
    volume = {57},
    month = jun,
    pages = {1838--1852},
    year = {2013},
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/rossi13comnet.pdf}
  }
  

  BitTorrent has recently introduced LEDBAT, a novel application-layer congestion control protocol for data exchange. The protocol design assumes that network bottlenecks are at the access of the network, and that thus user traffic competes creating self-induced congestion. To relieve this phenomenon, LEDBAT is designed to quickly infer when self-induced congestion is approaching (by detecting relative changes of the one-way delay in the transmission path), and to react promptly by reducing the sending rate prior to the congestion occurrence. Previous work has however shown LEDBAT to be affected by a latecomer advantage, where newly arriving connections can starve already existing flows. In this work, we propose modifications to the congestion window update mechanism of LEDBAT that solve this issue, thus guaranteeing intra-protocol fairness and efficiency. Closed-form expressions for the stationary throughput and queue occupancy are provided via a fluid model, whose accuracy is confirmed by means of ns2 packet level simulations. Our results show that the proposed change can effectively solve the latecomer issue, furthermore without affecting the other original LEDBAT goals.
• [ICN-13] , "INFORM: a Dynamic Interest Forwarding Mechanism for Information Centric Networking" ACM SIGCOMM Worskhop on Information-Centric Networking (ICN) 2013, Conference Abstract Bibtex

  @inproceedings{DR:ICN-13,
    title = {{INFORM: a Dynamic Interest Forwarding Mechanism for Information Centric Networking}},
    author = {},
    booktitle = {ACM SIGCOMM Worskhop on Information-Centric Networking (ICN)},
    year = {2013},
    address = {Hong Kong, China},
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/rossi13icn.pdf}
  }
  

  Information Centric Networking is a new communication paradigm where network primitives are based on named-data rather than host identifiers. In ICN, data retrieval is triggered by user requests which are forwarded towards a copy of the desired content item. Data can be retrieved either from a server that permanently provides a content item, or from a temporary item copy opportunistically cached by an in-network node. As the availability of cached items dynamically varies over time, the request forwarding scheme should be adapted accordingly. In this paper we focus on dynamic request forwarding in ICN, and develop an approach, inspired by Q-routing framework, that we show to outperform algorithms currently available in the state of the art.
• [COMNET-13b] Rossini, Giuseppe and Rossi, Dario and Betoule, Christophe and Clavier, Remi and Thouenon, Gilles, "FIB Aplasia through Probabilistic Routing and Autoforwarding" In Elsevier Computer Networks, Vol. 57, pp.2802–2816, 2013, Journal Bibtex

  @article{DR:COMNET-13b,
    title = {FIB Aplasia through Probabilistic Routing and Autoforwarding},
    author = {Rossini, Giuseppe and Rossi, Dario and Betoule, Christophe and Clavier, Remi and Thouenon, Gilles},
    year = {2013},
    volume = {57},
    pages = {2802--2816},
    issue = {14},
    journal = {Elsevier Computer Networks},
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/rossi13comnet-b.pdf}
  }
  
• [PATENT-06] Perino, D. and Carofiglio, G. and Rossi, D. and Rossini, G., "Dynamic Interest Forwarding Mechanism for Information Centric Networking" , https://perso.telecom-paristech.fr/drossi/paper/MISSINGURL.pdf . 2013, Patent

  @misc{DR:PATENT-06,
    author = {Perino, D. and Carofiglio, G. and Rossi, D. and Rossini, G.},
    title = {Dynamic Interest Forwarding Mechanism for Information Centric Networking},
    address = {},
    year = {2013},
    month = {},
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/MISSINGURL.pdf}
  }
  
• [PATENT-05] Perino, D. and Carofiglio, G. and Chiocchetti, R. and Rossi, D. and Rossini, G., "Device and method for organizing forwarding information in nodes of a content centric networking" , https://perso.telecom-paristech.fr/drossi/paper/MISSINGURL.pdf . 2013, Patent

  @misc{DR:PATENT-05,
    author = {Perino, D. and Carofiglio, G. and Chiocchetti, R. and Rossi, D. and Rossini, G.},
    title = {Device and method for organizing forwarding information in nodes of a content centric networking},
    address = {},
    year = {2013},
    month = {},
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/MISSINGURL.pdf}
  }
  
• [PATENT-11] Perino, D. and Carofiglio, G. and Rossi, D. and Rossini, G., "Dynamic Interest Forwarding Mechanism for Information Centric Networking" , Patent EPO13306124.2 . 2013, Patent

  @misc{DR:PATENT-11,
    author = {Perino, D. and Carofiglio, G. and Rossi, D. and Rossini, G.},
    title = {Dynamic Interest Forwarding Mechanism for Information Centric Networking},
    howpublished = {Patent EPO13306124.2},
    address = {},
    year = {2013},
    month = {},
    volume = {},
    number = {},
    pages = {},
    annote = {}
  }
  
• [PATENT-12] Perino, D. and Carofiglio, G. and Chiocchetti, R. and Rossi, D. and Rossini, G., "Device and method for organizing forwarding information in nodes of a content centric networking" , Patent EPO13161714.4 . 2013, Patent

  @misc{DR:PATENT-12,
    author = {Perino, D. and Carofiglio, G. and Chiocchetti, R. and Rossi, D. and Rossini, G.},
    title = {Device and method for organizing forwarding information in nodes of a content centric networking},
    howpublished = {Patent EPO13161714.4},
    address = {},
    year = {2013},
    month = {},
    volume = {},
    number = {},
    pages = {},
    annote = {}
  }
  
• [COMCOM-13] Rossini, Giuseppe and Rossi, Dario, "Evaluating CCN multi-path interest forwarding strategies" In Elsevier Computer Communication, SI on Information Centric Networking,, Vol. 36, pp.771-778, Avril. 2013, Journal Abstract Bibtex

  @article{DR:COMCOM-13,
    author = {Rossini, Giuseppe and Rossi, Dario},
    title = {Evaluating CCN multi-path interest forwarding strategies},
    journal = {Elsevier Computer Communication, SI on Information Centric Networking,},
    month = {Avril},
    volume = {36},
    issue = {7},
    pages = {771-778},
    year = {2013},
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/rossi13comcom.pdf}
  }
  

  This work addresses the performance evaluation of Content Centric Networks (CCN). Focusing on a realistic YouTube-like catalog, we conduct a thorough simulation study of the main system performance, with a special focus on multi-path interest forwarding strategies but thoroughly analyzing the impact of several other ingredients – such as network topology, content popularity, caching decisions and replacement policies. Summarizing our main results, (i) catalog and popularity settings play by far the most crucial role (ii) the impact of the strategy layer comes next, with naive forwarding strategies playing against CCN efficiency, (iii) simple randomized caching policies perform almost as well as more complex ones, (iv) the impact of the topology is limited. Hopefully, our thorough assessment of scenario parameters can assist and promote the cross-comparison in the research community – for which we also provide our CCN simulator as open source software.
• [IJNM-12] , "Exploiting packet sampling measurements for traffic characterization and classification" In International Journal of Network Management, pp.451-476, nov. 2012, DOI 10.1002/nem.1802 Journal Abstract Bibtex

  @article{DR:IJNM-12,
    author = {},
    title = {Exploiting packet sampling measurements for traffic characterization and classification},
    journal = {International Journal of Network Management},
    month = nov,
    vol = {22},
    issue = {6},
    year = {2012},
    pages = {451-476},
    doi = {10.1002/nem.1802},
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/rossi12ijnm.pdf}
  }
  

  The use of packet sampling for traffic measurement has become mandatory for network operators to cope with the huge amount of data transmitted in nowadays networks, powered by increasingly faster transmission technologies. Therefore, many networking tasks must already deal with such reduced data, more available but less rich in information. In this work we assess the impact of packet sampling on various network monitoring activities, with a particular focus on traffic characterization and classification. We process an extremely heterogeneous dataset composed of four packet level traces (representative of different access technologies and operational environments) with a traffic monitor able to apply different sampling policies and rates to the traffic and extract several features both in aggregated and per-flow fashion, providing empirical evidences of the impact of packet sampling on both traffic measurement and traffic classification. First, we analyze feature distortion, quantified by means of two statistical metrics: most features appear already deteriorated under low sampling step, no matter the sampling policy, while only a few remain consistent under harsh sampling conditions, which may even cause some artifacts undermining the correctness of measurements. Second, we evaluate the performance of traffic classification under sampling. The information content of features, even though deteriorated, still allows a good classification accuracy, provided that the classifier is trained with data obtained at the same sampling rate of the target data. The accuracy is also due to a thoughtful choice of a smart sampling policy which biases the sampling towards packets carrying the most useful information.
• [P2P-12] , "Inferring the buffering delay of remote BitTorrent peers under LEDBAT vs TCP" IEEE P2P’XII sep. 2012, Conference Abstract Bibtex

  @inproceedings{DR:P2P-12,
    title = {Inferring the buffering delay of remote {BitTorrent} peers under {LEDBAT} vs {TCP}},
    author = {},
    year = {2012},
    booktitle = {IEEE P2P'XII},
    month = sep,
    pages = {77-78},
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/rossi12p2p.pdf}
  }
  

  Nowadays, due to excessive queuing, Internet delays grow sometimes as large as the propagation delay from moon to earth – for which the bufferbloat term was recently coined. Some points to active queue management (AQM) as its solution, others propose end-to-end congestion control techniques – like BitTor- rent that recently replaced TCP with the LEDBAT transport protocol. In this demo, we implement a methodology to monitor the upstream queuing delay experienced by remote hosts, both those using LEDBAT, through LEDBAT’s native one-way delay mea- surements, and those using TCP, through the timestamp option. By actively taking part into torrent downloads as leechers, our software is able to infer (and visualize) the amount of access delay suffered by the remote peers.
• [CAMAD-12] G. Rossini, D. Rossi, "A dive into the caching performance of Content Centric Networking" IEEE 17th International Workshop on Computer Aided Modeling and Design of Communication Links and Networks (CAMAD’12) sep. 2012, Conference Abstract Bibtex

  @inproceedings{DR:CAMAD-12,
    title = {A dive into the caching performance of Content Centric Networking},
    author = {G. Rossini, D. Rossi},
    booktitle = {IEEE 17th International Workshop on Computer Aided Modeling and Design of Communication Links and Networks (CAMAD'12)},
    year = {2012},
    month = sep,
    pages = {105-109},
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/rossi12camad.pdf}
  }
  

  Content Centric Networking (CCN) is a promising architecture for the diffusion of popular content over the Internet. While CCN system design is sound, gathering a reliable estimate of its performance in the current Internet is challenging, due to the large scale and to the lack of agreement in some critical elements of the evaluation scenario. In this work, we add a number of important pieces to the CCN puzzle by means of a chunk-level simulator that we make available to the scientific community as open source software. First, we pay special attention to the locality of the user request process, as it may be determined by user interest or language barrier. Second, we consider the existence of possibly multiple repositories for the same content, as in the current Internet, along with different CCN interest forwarding policies, exploiting either a single or multiple repositories in parallel. To widen the relevance of our findings, we consider multi- ple topologies, content popularity settings, caching replacement policies and CCN forwarding strategies. Summarizing our main result, though the use of multiple content repositories can be beneficial from the user point of view, it may however counter part of the benefits if the CCN strategy layer implements naive interest forwarding policies.
• [ALGOTEL-12] Rossini, G. and Rossi, D., "Large scale simulation of CCN networks" Algotel 2012 may. 2012, Conference Abstract Bibtex

  @inproceedings{DR:ALGOTEL-12,
    author = {Rossini, G. and Rossi, D.},
    title = {Large scale simulation of CCN networks},
    booktitle = {Algotel 2012},
    year = {2012},
    address = {La Grande Motte, France},
    month = may,
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/rossi12algotel.pdf}
  }
  

  This work addresses the performance evaluation of Content Centric Networks (CCN). Focusing on a realistic YouTube-like catalog, we conduct a very thorough simulation study of the main system performance, consider several ingredients such as network topology, multi-path routing, content popularity, caching decisions and replacement policies. Summarizing our main results, we gather that (i) the impact of the topology is limited, (ii) multi-path routing may play against CCN efficiency, (iii) simple randomized policies perform almost as well as more complex ones, (iv) catalog and popularity settings play by far the most crucial role above all. Hopefully, our thorough assessment of scenario parameters can assist and promote the cross-comparison in the research community – for which we also provide our CCN simulator as open source software.
• [TMA-12] Testa, C. and Rossi, D. and Rao, A. and Legout, A., "Experimental Assessment of BitTorrent Completion Time in Heterogeneous TCP/uTP swarms" Traffic Measurement and Analysis (TMA) Workshop at Passive and Active Measurement (PAM) mar. 2012, Conference Abstract Bibtex

  @inproceedings{DR:TMA-12,
    author = {Testa, C. and Rossi, D. and Rao, A. and Legout, A.},
    title = {Experimental Assessment of BitTorrent Completion Time in Heterogeneous TCP/uTP swarms},
    booktitle = {Traffic Measurement and Analysis (TMA) Workshop at Passive and Active Measurement (PAM)},
    year = {2012},
    pages = {52-56},
    address = {Wien, AU},
    month = mar,
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/rossi12tma.pdf}
  }
  

  BitTorrent, one of the most widespread used P2P application for file- sharing, recently got rid of TCP by introducing an application-level congestion control protocol named uTP. The aim of this new protocol is to efficiently use the available link capacity, while minimizing its interference with the rest of user traffic (e.g., Web, VoIP and gaming) sharing the same access bottleneck. In this paper we perform an experimental study of the impact of uTP on the torrent completion time, the metric that better captures the user experience. We run BitTorrent applications in a flash crowd scenario over a dedicated cluster platform, under both homogeneous and heterogeneous swarm population. Exper- iments show that an all-uTP swarms have shorter torrent download time with respect to all-TCP swarms. Interestingly, at the same time, we observe that even shorter completion times can be achieved under mixtures of TCP and uTP traffic, as in the default BitTorrent settings.
• [NOMEN-12] Rossi, D. and Rossini, G., "On sizing CCN content stores by exploiting topological information" IEEE INFOCOM, NOMEN Worshop, mar. 2012, Conference Abstract Bibtex

  @inproceedings{DR:NOMEN-12,
    author = {Rossi, D. and Rossini, G.},
    title = {On sizing CCN content stores by exploiting topological information},
    booktitle = {IEEE INFOCOM, NOMEN Worshop,},
    year = {2012},
    address = {Orlando, FL},
    pages = {280-285},
    month = mar,
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/rossi12nomen.pdf}
  }
  

  In this work, we study the caching performance of Content Centric Networking (CCN), with special emphasis on the size of individual CCN router caches. Specifically, we consider several graph-related centrality metrics (e.g., betweenness, closeness, stress, graph, eccentricity and degree centralities) to allocate content store space heterogeneously across the CCN network, and contrast the performance to that of an homogeneous allocation. To gather relevant results, we study CCN caching performance under large cache sizes (individual content stores of 10 GB), realistic topologies (up to 60 nodes), a YouTube-like Internet catalog (108 files for 1PB video data). A thorough simulation campaign allow us to conclude that (i) , the gain brought by content store size heterogeneity is very limited, and that (ii) the simplest metric, namely degree centrality, already proves to be a “sufficiently good” allocation criterion. On the one hand, this implies rather simple rules of thumb for the content store sizing (e.g., “if you add a line card to a CCN router, add some content store space as well”). On the other hand, we point out that technological constraints, such as line- speed operation requirement, may however limit the applicability of degree-based content store allocation.
• [IETF83-b] Rossi, Dario, "Traffic classification under sampling" Talk at IETF83, NMRG Workshop mar. 2012, Conference Bibtex

  @inproceedings{DR:IETF83-b,
    author = {Rossi, Dario},
    title = {Traffic classification under sampling},
    booktitle = {Talk at IETF83, NMRG Workshop},
    month = mar,
    year = {2012},
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/rossi12nmrg-ietf83.pdf}
  }
  
• [IETF83-a] Rossi, Dario, "A dive into CCN^⋆caching performance" Talk at IETF83, ICNRG meeting mar. 2012, Conference Bibtex

  @inproceedings{DR:IETF83-a,
    author = {Rossi, Dario},
    title = {A dive into CCN$^\star$ caching performance},
    booktitle = {Talk at IETF83, ICNRG meeting},
    month = mar,
    year = {2012},
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/rossi12icnrg-ietf83.pptx}
  }
  
• [NTMS-12] , "Adaptive Probabilistic Flooding for Multi-path Routing" IFIP NTMS, Best paper award 2012, Conference Abstract Bibtex

  @inproceedings{DR:NTMS-12,
    author = {},
    title = {Adaptive Probabilistic Flooding for Multi-path Routing},
    booktitle = {IFIP NTMS, Best paper award},
    year = {2012},
    pages = {1-6},
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/rossi12ntms.pdf}
  }
  

  In this work, we develop a distributed routing algorithm for topology discovery, suitable for ISP transport networks, that is however inspired by opportunistic algorithms used in ad hoc wireless networks. We propose a plug-and-play control plane, able to find multiple paths toward the same destination, and introduce a novel algorithm, called adaptive probabilistic flooding, to achieve this goal. By keeping a small amount of state in routers taking part in the discovery process, our technique significantly limits the amount of control messages exchanged with flooding \u2013 and, at the same time, it only minimally affects the quality of the discovered multiple path with respect to the optimal solution. Simple analytical bounds, confirmed by results gathered with extensive simulation on several topologies (up to 10,000 nodes), show our approach to be of high practical interest.
• [SBE-12] , "The Green-Game: Accounting for Device Criticality in Resource Consolidation for Backbone IP Networks" In Strategic Behavior and the Environment, SI on ICT-based strategies for environmental conflicts, 2012, Journal Bibtex

  @article{DR:SBE-12,
    author = {},
    title = {The Green-Game: Accounting for Device Criticality in Resource Consolidation for Backbone IP Networks},
    journal = {Strategic Behavior and the Environment, SI on ICT-based strategies for environmental conflicts},
    year = {2012},
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/rossi12sbe.pdf}
  }
  
• [ICN-12] Chiocchetti, Raffaele and Rossi, Dario and Rossini, Giuseppe and Carofiglio, Giovanna and Diego Perino, "Exploit the known or explore the unknown: Hamlet-like doubts in ICN" ACM SIGCOMM, ICN Workshop, 2012, Conference Bibtex

  @inproceedings{DR:ICN-12,
    author = {Chiocchetti, Raffaele and Rossi, Dario and Rossini, Giuseppe and Carofiglio, Giovanna and Diego Perino},
    title = {Exploit the known or explore the unknown: Hamlet-like doubts in ICN},
    booktitle = {ACM SIGCOMM, ICN Workshop,},
    year = {2012},
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/rossi12icn.pdf}
  }
  
• [GREENBOOKCH-12] A. P. Bianzino, A. K. Raju, D. Rossi, "Energy Consumption in the Internet Core: a Sensitivity Analysis" 2012, Bookch Bibtex

  @inbook{DR:GREENBOOKCH-12,
    author = {A. P. Bianzino, A. K. Raju, D. Rossi},
    booktitle = {Sustainable Green Computing: Practices, Methodologies and Technologies},
    title = {Energy Consumption in the Internet Core: a Sensitivity Analysis},
    editor = {Naima, K. and Chen, W.},
    publisher = {IGI Global},
    address = {Hershey, Pennsylvania (USA)},
    year = {2012},
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/rossi11greenbookch.pdf}
  }
  
• [ITC-23] Bianzino, Aruna Prem and Chaudet, Claude and Rossi, Dario and Rougier, Jean-Louis and Moretti, Stefano, "The Green-Game: Striking a Balance between QoS and Energy Saving" 23rd International Teletraffic Congress (ITC23) sep. 2011, Conference Bibtex

  @inproceedings{DR:ITC-23,
    author = {Bianzino, Aruna Prem and Chaudet, Claude and Rossi, Dario and Rougier, Jean-Louis and Moretti, Stefano},
    title = {The Green-Game: Striking a Balance between QoS and Energy Saving},
    booktitle = {23rd International Teletraffic Congress (ITC23)},
    month = sep,
    year = {2011},
    location = {San Francisco, USA},
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/rossi11itc.pdf}
  }
  
• [NETWORK-11] , "Experiences of Internet Traffic Monitoring with Tstat" In IEEE Network Magazine, Special Issue on Network Traffic Monitoring and Analysis, may. 2011, Journal Bibtex

  @article{DR:NETWORK-11,
    author = {},
    title = {Experiences of Internet Traffic Monitoring with Tstat},
    journal = {IEEE Network Magazine, Special Issue on Network Traffic Monitoring and Analysis},
    year = {2011},
    month = may,
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/rossi11network.pdf}
  }
  
• [PER-11] Bianzino, Aruna Prem and Raju, Anand Kishore and Rossi, Dario, "Apples-to-apples: a framework analysis for energy-efficiency in networks" In SIGMETRICS Perform. Eval. Rev., Vol. 38, pp.81–85, jan. 2011, DOI http://doi.acm.org/10.1145/1925019.1925036 Journal Bibtex

  @article{DR:PER-11,
    author = {Bianzino, Aruna Prem and Raju, Anand Kishore and Rossi, Dario},
    title = {Apples-to-apples: a framework analysis for energy-efficiency in networks},
    journal = {SIGMETRICS Perform. Eval. Rev.},
    volume = {38},
    issue = {3},
    month = jan,
    year = {2011},
    issn = {0163-5999},
    pages = {81--85},
    numpages = {5},
    doi = {http://doi.acm.org/10.1145/1925019.1925036},
    acmid = {1925036},
    publisher = {ACM},
    address = {New York, NY, USA},
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/MISSINGURL.pdf}
  }
  
• [ITPRO-11] Raju, A. and Bianzino, A. P. and Rossi, D., "Greening the Internet: Measuring Web Power Consumption" In IEEE ITProfessional, jan. 2011, Journal Bibtex

  @article{DR:ITPRO-11,
    author = {Raju, A. and Bianzino, A. P. and Rossi, D.},
    title = {Greening the Internet: Measuring Web Power Consumption},
    journal = {IEEE ITProfessional},
    year = {2011},
    month = jan,
    vol = {13},
    issue = {1},
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/rossi11itpro.pdf}
  }
  
• [MODELNET-TR11] E. Alessandria, L. Muscariello, D. Rossi, "ModelNet-TE: An emulation tool for the study of P2P and Traffic Engineering interaction dynamics" Telecom ParisTech 2011, Tech.Rep. Bibtex

  @techreport{DR:MODELNET-TR11,
    title = {ModelNet-TE: An emulation tool for the study of P2P and Traffic Engineering interaction dynamics},
    author = {E. Alessandria, L. Muscariello, D. Rossi},
    institution = {Telecom ParisTech},
    year = {2011},
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/MISSINGURL.pdf}
  }
  
• [CCN-TR11a] D. Rossi, G. Rossini, "Caching performance of content centric networks under multi-path routing (and more)" Telecom ParisTech 2011, Tech.Rep. Bibtex

  @techreport{DR:CCN-TR11a,
    title = {Caching performance of content centric networks under multi-path routing (and more)},
    author = {D. Rossi, G. Rossini},
    institution = {Telecom ParisTech},
    year = {2011},
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/rossi11ccn-techrep1.pdf}
  }
  
• [LEDBAT-COLUMBIA] Rossi, D., "A crash course on LEDBAT, the new BitTorrent congestion control algorithm" Talk at Columbia University 2011, Tech.Rep. Bibtex

  @techreport{DR:LEDBAT-COLUMBIA,
    title = {A crash course on LEDBAT, the new BitTorrent congestion control algorithm},
    author = {Rossi, D.},
    institution = {Talk at Columbia University},
    year = {2011},
    date = {16th November},
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/rossi11ledbad_columbia.pdf}
  }
  
• [HDR-10] Rossi, Dario, "Peer-2-peer networking: the Dawn of the Homo Interconnexus Era" dec. 2010, Bibtex

  @hdrthesis{DR:HDR-10,
    title = {Peer-2-peer networking: the Dawn of the Homo Interconnexus Era},
    author = {Rossi, Dario},
    year = {2010},
    month = dec,
    school = {Universite Pierre et Marie Curie (UPMC)},
    howpublished = {http://perso.telecom-paristech.fr/~drossi/DATA/DRossi_HDRThesis.pdf}
  }
  
• [WWIC-10] Finamore, A. and Mellia, M. and Meo, M. and Munafo, M. and Rossi, D., "Live traffic monitoring with Tstat: capabilities and experiences" 8th International Conference on Wired/Wireless Communication (WWIC’10), Springer LNCS 6074, Invited Paper jun. 2010, Conference Bibtex

  @inproceedings{DR:WWIC-10,
    author = {Finamore, A. and Mellia, M. and Meo, M. and Munafo, M. and Rossi, D.},
    title = {{Live traffic monitoring with Tstat: capabilities and experiences}},
    booktitle = {8th International Conference on Wired/Wireless Communication (WWIC'10), Springer LNCS 6074, Invited Paper},
    address = {Lulea, Sweden},
    year = {2010},
    month = jun,
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/rossi10wwic.pdf}
  }
  
• [TECHREP-10b] Carofiglio, G. and Muscariello, L. and Rossi, D. and Testa, C. and Valenti, S., "Rethinking low extra delay backtround transport protocols" Telecom ParisTech 2010, Tech.Rep. Bibtex

  @techreport{DR:TECHREP-10b,
    title = {Rethinking low extra delay backtround transport protocols},
    author = {Carofiglio, G. and Muscariello, L. and Rossi, D. and Testa, C. and Valenti, S.},
    institution = {Telecom ParisTech},
    year = {2010},
    howpublished = {http://arxiv.org/pdf/1010.5623}
  }
  
• [IJNM-10] Birke, R. and Mellia, M. and Petracca, M. and Rossi, D., "Inspecting VoIP by Measurements from a Large ISP" In Wiley International Journal on Network Management, Special Issue on “Traffic Monitoring and Network Measurements: from Theory to Practice”, 2010, Journal Bibtex

  @article{DR:IJNM-10,
    author = {Birke, R. and Mellia, M. and Petracca, M. and Rossi, D.},
    title = {Inspecting VoIP by Measurements from a Large ISP},
    journal = {Wiley International Journal on Network Management, Special Issue on ``Traffic Monitoring and Network Measurements: from Theory to Practice''},
    year = {2010},
    editor = {F. Ricciato, P. Owezarski, M. Papadopouli (Eds)},
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/rossi10ijnm.pdf}
  }
  
• [WILEY-10] Rossi, D. and Fracchia, R. and Meo, M., "On the quality of broadcast services in vehicular ad hoc networks" In Wiley Security and Communication Networks Journal, Special Issue on QoS Assured Wireless and Mobile Networks, . 2010, Journal Bibtex

  @article{DR:WILEY-10,
    author = {Rossi, D. and Fracchia, R. and Meo, M.},
    title = {{On the quality of broadcast services in vehicular ad hoc networks}},
    journal = {Wiley Security and Communication Networks Journal, Special Issue on QoS Assured Wireless and Mobile Networks},
    year = {2010},
    month = {},
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/rossi10scnj.pdf}
  }
  
• [ICC-09b] Muscariello, L. and Perino, D. and Rossi, D., "Do Next Generation Networks need Path Diversity" IEEE International Conference on Communications (ICC’09) jun. 2009, Conference Bibtex

  @inproceedings{DR:ICC-09b,
    author = {Muscariello, L. and Perino, D. and Rossi, D.},
    title = {Do Next Generation Networks need Path Diversity},
    booktitle = {IEEE International Conference on Communications (ICC'09)},
    address = {Dresde, Germany},
    year = {2009},
    month = jun,
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/rossi09icc-b.pdf}
  }
  
• [ICC-09a] Rossi, D. and Mellia, M. and Meo, M., "Evidences Behind Skype Outage" IEEE International Conference on Communications (ICC’09) jun. 2009, Conference Bibtex

  @inproceedings{DR:ICC-09a,
    author = {Rossi, D. and Mellia, M. and Meo, M.},
    title = {Evidences Behind Skype Outage},
    booktitle = {IEEE International Conference on Communications (ICC'09)},
    address = {Dresde, Germany},
    year = {2009},
    month = jun,
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/rossi09icc-a.pdf}
  }
  
• [COMNET-09a] Bermolen, P. and Rossi, D., "Support Vector Regression for Link Load Prediction" In Elsevier Computer Networks, Vol. 53, No. 2, pp.191-202, feb. 2009, Journal Bibtex

  @article{DR:COMNET-09a,
    author = {Bermolen, P. and Rossi, D.},
    title = {Support Vector Regression for Link Load Prediction},
    journal = {Elsevier Computer Networks},
    year = {2009},
    month = feb,
    volume = {53},
    number = {2},
    pages = {191-202},
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/rossi09comnet-a.pdf}
  }
  
• [COMNET-09b] Rossi, D. and Mellia, M. and Meo, M., "Understanding Skype Signaling" In Elsevier Computer Networks, Vol. 53, No. 2, pp.130-140, feb. 2009, Journal Bibtex

  @article{DR:COMNET-09b,
    author = {Rossi, D. and Mellia, M. and Meo, M.},
    title = {Understanding Skype Signaling},
    journal = {Elsevier Computer Networks},
    year = {2009},
    month = feb,
    volume = {53},
    number = {2},
    pages = {130-140},
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/rossi09comnet-b.pdf}
  }
  
• [TOM-09b] Bonfiglio, D. and Mellia, M. and Meo, M. and D.Rossi, "Detailed Analysis of Skype Traffic" In IEEE Transaction on Multimedia, Vol. 11, No. 1, pp.117-127, jan. 2009, Journal Bibtex

  @article{DR:TOM-09b,
    author = {Bonfiglio, D. and Mellia, M. and Meo, M. and D.Rossi},
    title = {Detailed Analysis of Skype Traffic},
    journal = {IEEE Transaction on Multimedia},
    year = {2009},
    month = jan,
    volume = {11},
    number = {1},
    pages = {117-127},
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/rossi09tmm.pdf}
  }
  
• [RECIPE-09] Finamore, A. and Mellia, M. and Meo, M. and Rossi, D., "KISS: Stochastic Packet Inspection for UDP Traffic Classification" 2009, Bookch Bibtex

  @inbook{DR:RECIPE-09,
    author = {Finamore, A. and Mellia, M. and Meo, M. and Rossi, D.},
    title = {KISS: Stochastic Packet Inspection for UDP Traffic Classification},
    booktitle = {RECIPE: Robust and Efficient Traffic Classification in IP Networks},
    editor = {Pescape, A. and Eds., C. Sansone},
    publisher = {Fridericiana Editrice Universitaria},
    isbn = {9788883380815},
    address = {Napoli, Italy},
    year = {2009},
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/MISSINGURL.pdf}
  }
  
• [FITraMEn-08] Bermolen, P. and Rossi, D., "Network Forecast with Support Vector Machines" International Workshop on Traffic Management and Traffic Engineering for the Future Internet (FITraMEn 08) dec. 2008, Conference Bibtex

  @inproceedings{DR:FITraMEn-08,
    author = {Bermolen, P. and Rossi, D.},
    title = {Network Forecast with Support Vector Machines},
    booktitle = {International Workshop on Traffic Management and Traffic Engineering for the Future Internet (FITraMEn 08)},
    address = {Porto, Portugal},
    year = {2008},
    month = dec,
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/MISSINGURL.pdf}
  }
  
• [COMNET-08] Mellia, M. and Meo, M. and Muscariello, L. and Rossi, D., "Passive analysis of TCP anomalies" In Elsevier Computer Networks, Vol. 52, No. 14, oct. 2008, Journal Bibtex

  @article{DR:COMNET-08,
    author = {Mellia, M. and Meo, M. and Muscariello, L. and Rossi, D.},
    title = {Passive analysis of TCP anomalies},
    journal = {Elsevier Computer Networks},
    year = {2008},
    month = oct,
    volume = {52},
    number = {14},
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/rossi08comnet.pdf}
  }
  
• [PER-08] Rossi, D. and Valenti, S. and Veglia, P. and Bonfiglio, D. and Mellia, M. and Meo, M., "Pictures from the Skype" In ACM Performance Evaluation Review (PER), Vol. 36, No. 2, pp.83–86, sep. 2008, Journal Bibtex

  @article{DR:PER-08,
    author = {Rossi, D. and Valenti, S. and Veglia, P. and Bonfiglio, D. and Mellia, M. and Meo, M.},
    title = {Pictures from the Skype},
    journal = {ACM Performance Evaluation Review (PER)},
    year = {2008},
    month = sep,
    volume = {36},
    number = {2},
    pages = {83--86},
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/rossi08per.pdf}
  }
  
• [SIGMETRIC-08] Rossi, D. and Valenti, S. and Veglia, P. and Bonfiglio, D. and Mellia, M. and Meo, M., "Pictures from the Skype" ACM SIGMETRICS, Demo Competition jun. 2008, Conference Bibtex

  @inproceedings{DR:SIGMETRIC-08,
    author = {Rossi, D. and Valenti, S. and Veglia, P. and Bonfiglio, D. and Mellia, M. and Meo, M.},
    title = {Pictures from the Skype},
    booktitle = {ACM SIGMETRICS, Demo Competition},
    address = {Annapolis, MD, USA},
    year = {2008},
    month = jun,
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/rossi08sigmetrics.pdf}
  }
  
• [ICC-08] Rossi, D. and Fracchia, R. and Meo, M., "VANETs: Why Beaconing at All" IEEE International Conference on Communications (ICC’08) may. 2008, Conference Bibtex

  @inproceedings{DR:ICC-08,
    author = {Rossi, D. and Fracchia, R. and Meo, M.},
    title = {{VANET}s: Why Beaconing at All},
    booktitle = {IEEE International Conference on Communications (ICC'08)},
    address = {Beijing, China},
    year = {2008},
    month = may,
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/rossi08icc.pdf}
  }
  
• [INFOCOM-08] Bonfiglio, D. and Mellia, M. and Meo, M. and Ritacca, N. and Rossi, D., "Tracking Down Skype Traffic" IEEE INFOCOM apr. 2008, Conference Bibtex

  @inproceedings{DR:INFOCOM-08,
    author = {Bonfiglio, D. and Mellia, M. and Meo, M. and Ritacca, N. and Rossi, D.},
    title = {{Tracking Down Skype Traffic}},
    booktitle = {{IEEE INFOCOM}},
    address = {Phoenix, AZ, USA},
    year = {2008},
    month = apr,
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/rossi08infocom.pdf}
  }
  
• [QoSIP-08a] D.Rossi and M.Mellia and M.Meo, "Following Skype Signaling Footsteps" IEEE QoS-IP feb. 2008, Conference Bibtex

  @inproceedings{DR:QoSIP-08a,
    author = {D.Rossi and M.Mellia and M.Meo},
    title = {{Following Skype Signaling Footsteps}},
    booktitle = {{IEEE QoS-IP}},
    address = {Venezia, Italy},
    year = {2008},
    month = feb,
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/rossi08itnews-a.pdf}
  }
  
• [IPTPS-08] Rossi, D. and Mellia, M. and Meo, M., "A Detailed Measurement of Skype Network Traffic" 7th International Worshop on P2P Systems (IPTPS) feb. 2008, Conference Bibtex

  @inproceedings{DR:IPTPS-08,
    author = {Rossi, D. and Mellia, M. and Meo, M.},
    title = {A Detailed Measurement of Skype Network Traffic},
    booktitle = {7th International Worshop on P2P Systems (IPTPS)},
    address = {Tampa Bay (FL)},
    year = {2008},
    month = feb,
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/rossi08iptps.pdf}
  }
  
• [QoSIP-08b] Bermolen, P. and Rossi, D., "Support Vector Regression for Link Load Prediction" IEEE QoS-IP feb. 2008, Conference Bibtex

  @inproceedings{DR:QoSIP-08b,
    author = {Bermolen, P. and Rossi, D.},
    title = {{Support Vector Regression for Link Load Prediction}},
    booktitle = {{IEEE QoS-IP}},
    address = {Venezia, Italy},
    year = {2008},
    month = feb,
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/rossi08itnews-b.pdf}
  }
  
• [PATENT-04] Perino, M. and Mellia, M. and Rossi, D. and Meo, M., "Method and apparatus for detecting a single data flow in an aggregate packet data flow and for identifying the application generating said single data flow" , https://perso.telecom-paristech.fr/drossi/paper/MISSINGURL.pdf . 2008, Patent

  @misc{DR:PATENT-04,
    author = {Perino, M. and Mellia, M. and Rossi, D. and Meo, M.},
    title = {Method and apparatus for detecting a single data flow in an aggregate packet data flow and for identifying the application generating said single data flow},
    address = {},
    year = {2008},
    month = {},
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/MISSINGURL.pdf}
  }
  
• [PATENT-03] Perino, M. and Mellia, M. and Rossi, D. and Meo, M., "Method and apparatus for detecting vocal data flow in a packet data flow" , https://perso.telecom-paristech.fr/drossi/paper/MISSINGURL.pdf . 2008, Patent

  @misc{DR:PATENT-03,
    author = {Perino, M. and Mellia, M. and Rossi, D. and Meo, M.},
    title = {Method and apparatus for detecting vocal data flow in a packet data flow},
    address = {},
    year = {2008},
    month = {},
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/MISSINGURL.pdf}
  }
  
• [PATENT-13] Perino, M. and Mellia, M. and Rossi, D. and Meo, M., "Method and apparatus for detecting a single data flow in an aggregate packet data flow and for identifying the application generating said single data flow" , Patent WO2008149203 . 2008, Patent

  @misc{DR:PATENT-13,
    author = {Perino, M. and Mellia, M. and Rossi, D. and Meo, M.},
    title = {Method and apparatus for detecting a single data flow in an aggregate packet data flow and for identifying the application generating said single data flow},
    howpublished = {Patent WO2008149203},
    address = {},
    year = {2008},
    month = {},
    volume = {},
    number = {},
    pages = {},
    annote = {}
  }
  
• [PATENT-14] Perino, M. and Mellia, M. and Rossi, D. and Meo, M., "Method and apparatus for detecting vocal data flow in a packet data flow" , Patent WO2008075167 . 2008, Patent

  @misc{DR:PATENT-14,
    author = {Perino, M. and Mellia, M. and Rossi, D. and Meo, M.},
    title = {Method and apparatus for detecting vocal data flow in a packet data flow},
    howpublished = {Patent WO2008075167},
    address = {},
    year = {2008},
    month = {},
    volume = {},
    number = {},
    pages = {},
    annote = {}
  }
  
• [MEDIA200-08] Rossi, D. and Mellia, M. and Meo, M., "Quando il PC diventa un telefono" In Il Sole 24 ore / Media 2000,, . 2008, Journal Bibtex

  @article{DR:MEDIA200-08,
    author = {Rossi, D. and Mellia, M. and Meo, M.},
    title = {Quando il PC diventa un telefono},
    journal = {Il Sole 24 ore / Media 2000,},
    year = {2008},
    month = {},
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/MISSINGURL.pdf}
  }
  
• [INFOCOM-07] Birke, R. and Mellia, M. and Petracca, M. and Rossi, D., "Understanding VoIP from Backbone Measurements" IEEE INFOCOM may. 2007, Conference Bibtex

  @inproceedings{DR:INFOCOM-07,
    author = {Birke, R. and Mellia, M. and Petracca, M. and Rossi, D.},
    title = {{Understanding VoIP from Backbone Measurements}},
    booktitle = {{IEEE INFOCOM}},
    address = {Anchorage, Alaska, USA},
    year = {2007},
    month = may,
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/rossi07infocom.pdf}
  }
  
• [SIGCOMM-07] Bonfiglio, D. and Mellia, M. and Meo, M. and Rossi, D. and Tofanelli, P., "Revealing Skype Traffic: When Randomness Plays with You" In ACM SIGCOMM Computer Communication Review, Vol. 37, No. 4, pp.37-48, 2007, Journal Bibtex

  @article{DR:SIGCOMM-07,
    author = {Bonfiglio, D. and Mellia, M. and Meo, M. and Rossi, D. and Tofanelli, P.},
    title = {Revealing Skype Traffic: When Randomness Plays with You},
    journal = {ACM SIGCOMM Computer Communication Review},
    volume = {37},
    number = {4},
    pages = {37-48},
    year = {2007},
    ar = {10%},
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/rossi07sigcomm.pdf}
  }
  
• [PATENT-02] Perino, M. and Mellia, M. and Rossi, D. and Meo, M., "Metodo per rilevare un singolo flusso dati all’interno di un flusso aggregato di dati a pacchetti e per identificare l’applicazione generatrice del singolo flusso dati" , https://perso.telecom-paristech.fr/drossi/paper/MISSINGURL.pdf . 2007, Patent

  @misc{DR:PATENT-02,
    author = {Perino, M. and Mellia, M. and Rossi, D. and Meo, M.},
    title = {Metodo per rilevare un singolo flusso dati all'interno di un flusso aggregato di dati a pacchetti e per identificare l'applicazione generatrice del singolo flusso dati},
    address = {},
    year = {2007},
    month = {},
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/MISSINGURL.pdf}
  }
  
• [PATENT-15] Perino, M. and Mellia, M. and Rossi, D. and Meo, M., "Metodo per rilevare un singolo flusso dati all’interno di un flusso aggregato di dati a pacchetti e per identificare l’applicazione generatrice del singolo flusso dati" , Patent MI2007A001141 . 2007, Patent

  @misc{DR:PATENT-15,
    author = {Perino, M. and Mellia, M. and Rossi, D. and Meo, M.},
    title = {Metodo per rilevare un singolo flusso dati all'interno di un flusso aggregato di dati a pacchetti e per identificare l'applicazione generatrice del singolo flusso dati},
    howpublished = {Patent MI2007A001141},
    address = {},
    year = {2007},
    month = {},
    volume = {},
    number = {},
    pages = {},
    annote = {}
  }
  
• [SPRINGER-07] Rossi, D. and Casetti, C. and Chiasserini, C.F., "Some Study on Communication Performance" 2007, Bookch Bibtex

  @inbook{DR:SPRINGER-07,
    author = {Rossi, D. and Casetti, C. and Chiasserini, C.F.},
    booktitle = {Sensor Network and Configuration},
    title = {Some Study on Communication Performance},
    editor = {Ed., N.P. Mahalik},
    publisher = {Springer-Verlag},
    address = {Berlin, Germany},
    year = {2007},
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/MISSINGURL.pdf}
  }
  
• [AUTONET-06] Fracchia, R. and Meo, M. and Rossi, D., "VANETs: To Beacon or Not To Beacon" Autonet’06 Workshop at IEEE Globecom’06 nov. 2006, Conference Bibtex

  @inproceedings{DR:AUTONET-06,
    author = {Fracchia, R. and Meo, M. and Rossi, D.},
    title = {VANETs: To Beacon or Not To Beacon},
    booktitle = {Autonet'06 Workshop at IEEE Globecom'06},
    address = {San Francisco, CA, USA},
    year = {2006},
    month = nov,
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/rossi06autonet.pdf}
  }
  
• [ICC-06b] Rossi, D. and Mellia, M., "Real-Time TCP/IP Analysis with Common Hardware" IEEE International Conference of Communication (ICC’06) jun. 2006, Conference Bibtex

  @inproceedings{DR:ICC-06b,
    author = {Rossi, D. and Mellia, M.},
    title = {Real-Time TCP/IP Analysis with Common Hardware},
    booktitle = {IEEE International Conference of Communication (ICC'06)},
    address = {Istanbul, Turkey},
    year = {2006},
    month = jun,
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/rossi06icc-b.pdf}
  }
  
• [MEDHOC-06] Fracchia, R. and Meo, M. and Rossi, D., "On the Impact of Traffic Models on Inter-vehicular Broadcast Communication" IEEE MedHocNet 2006 jun. 2006, Conference Bibtex

  @inproceedings{DR:MEDHOC-06,
    author = {Fracchia, R. and Meo, M. and Rossi, D.},
    title = {On the Impact of Traffic Models on Inter-vehicular Broadcast Communication},
    booktitle = {IEEE MedHocNet 2006},
    address = {Lipari, Italy},
    year = {2006},
    month = jun,
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/rossi06medhocnet.pdf}
  }
  
• [ICC-06a] Muscariello, L. and Meo, M. and Mellia, M. and Rossi, D., "Passive Measurement of TCP Anomalies," IEEE International Conference of Communication (ICC’06) jun. 2006, Conference Bibtex

  @inproceedings{DR:ICC-06a,
    author = {Muscariello, L. and Meo, M. and Mellia, M. and Rossi, D.},
    title = {Passive Measurement of TCP Anomalies,},
    booktitle = {IEEE International Conference of Communication (ICC'06)},
    address = {Istanbul, Turkey},
    year = {2006},
    month = jun,
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/rossi06icc-a.pdf}
  }
  
• [ASWN-06] Fracchia, R. and Meo, M. and Rossi, D., "Avoiding broadcast storms in inter-vehicular warning delivery services" 6th International Workshop on Applications and Services in Wireless Networks (ASWN’06) apr. 2006, Conference Bibtex

  @inproceedings{DR:ASWN-06,
    author = {Fracchia, R. and Meo, M. and Rossi, D.},
    title = {Avoiding broadcast storms in inter-vehicular warning delivery services},
    booktitle = {6th International Workshop on Applications and Services in Wireless Networks (ASWN'06)},
    address = {Berlin, Germany},
    year = {2006},
    month = apr,
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/rossi06aswn.pdf}
  }
  
• [MP2P-06] Fracchia, R. and Meo, M. and Rossi, D., "Knowing Vehicle Location HELPs Avoiding Broadcast Packets Storm" 3rd IEEE International Workshop on Mobile Peer-to-Peer Computing (MP2P’06) at IEEE PerComm’06 mar. 2006, Conference Bibtex

  @inproceedings{DR:MP2P-06,
    author = {Fracchia, R. and Meo, M. and Rossi, D.},
    title = {Knowing Vehicle Location HELPs Avoiding Broadcast Packets Storm},
    booktitle = {3rd IEEE International Workshop on Mobile Peer-to-Peer Computing (MP2P'06) at IEEE PerComm'06},
    address = {Pisa, Italy},
    year = {2006},
    month = mar,
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/rossi06mp2p.pdf}
  }
  
• [PATENT-16] Perino, M. and Mellia, M. and Rossi, D. and Meo, M., "Metodo ed apparato per rilevare flusso dati vocale in un flusso dati a pacchetti" , Patent MI2006A002417 . 2006, Patent

  @misc{DR:PATENT-16,
    author = {Perino, M. and Mellia, M. and Rossi, D. and Meo, M.},
    title = {Metodo ed apparato per rilevare flusso dati vocale in un flusso dati a pacchetti},
    howpublished = {Patent MI2006A002417},
    address = {},
    year = {2006},
    month = {},
    volume = {},
    number = {},
    pages = {},
    annote = {}
  }
  
• [PATENT-01] Perino, M. and Mellia, M. and Rossi, D. and Meo, M., "Metodo ed apparato per rilevare flusso dati vocale in un flusso dati a pacchetti" , https://perso.telecom-paristech.fr/drossi/paper/MISSINGURL.pdf . 2006, Patent

  @misc{DR:PATENT-01,
    author = {Perino, M. and Mellia, M. and Rossi, D. and Meo, M.},
    title = {Metodo ed apparato per rilevare flusso dati vocale in un flusso dati a pacchetti},
    address = {},
    year = {2006},
    month = {},
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/MISSINGURL.pdf}
  }
  
• [NGI-05] Rossi, D. and Mellia, M., "Persistent Gbps Link Monitoring with Tstat" 2nd EuroNGI Workshop on New Trends in Modelling, Quantitative Methods and Measurements (WP IA.8.1) nov. 2005, Conference Bibtex

  @inproceedings{DR:NGI-05,
    author = {Rossi, D. and Mellia, M.},
    title = {Persistent Gbps Link Monitoring with Tstat},
    booktitle = {2nd EuroNGI Workshop on New Trends in Modelling, Quantitative Methods and Measurements (WP IA.8.1)},
    address = {Aveiro, Portugal},
    year = {2005},
    month = nov,
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/rossi05eurongi.pdf}
  }
  
• [GLOBECOM-05] Rossi, D. and Stoica, I., "Gambling Heuristics on a Chord Ring" IEEE Globecom’05 nov. 2005, Conference Bibtex

  @inproceedings{DR:GLOBECOM-05,
    author = {Rossi, D. and Stoica, I.},
    title = {Gambling Heuristics on a Chord Ring},
    booktitle = {IEEE Globecom'05},
    address = {St Luis, MO, USA},
    year = {2005},
    month = nov,
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/rossi05globecom.pdf}
  }
  
• [PHD-05] Rossi, D., "Traffic at the Network Edge: Sniff, Analyze, Act" apr. 2005, Bibtex

  @phdthesis{DR:PHD-05,
    author = {Rossi, D.},
    title = {Traffic at the Network Edge: Sniff, Analyze, Act},
    booktitle = {PhD Thesis, M. Ajmone Marsan Tutor,},
    address = {Politecnico di Torino},
    year = {2005},
    month = apr,
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/MISSINGURL.pdf}
  }
  
• [ICC-04] Rossi, D. and Muscariello, L. and Mellia, M., "On the properties of TCP Flow Arrival Process" IEEE International Conference of Communication (ICC’04) jun. 2004, Conference Bibtex

  @inproceedings{DR:ICC-04,
    author = {Rossi, D. and Muscariello, L. and Mellia, M.},
    title = {On the properties of TCP Flow Arrival Process},
    booktitle = {IEEE International Conference of Communication (ICC'04)},
    address = {Paris, France},
    year = {2004},
    month = jun,
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/rossi04icc.pdf}
  }
  
• [HPSR-04] Rossi, D. and Giaccone, P. and Muscariello, L. and Mellia, M., "The performance of Switch under Real Traffic" IEEE High Performance Switching and Routing (HPSR’04) apr. 2004, Conference Bibtex

  @inproceedings{DR:HPSR-04,
    author = {Rossi, D. and Giaccone, P. and Muscariello, L. and Mellia, M.},
    title = {The performance of Switch under Real Traffic},
    booktitle = {IEEE High Performance Switching and Routing (HPSR'04)},
    address = {Phoenix, AZ, USA},
    year = {2004},
    month = apr,
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/rossi04hpsr.pdf}
  }
  
• [GLOBECOM-03] Rossi, D. and Casetti, C. and Mellia, M., "User Patience and the Web: a Hands-on Investigation" IEEE Globecom’03 dec. 2003, Conference Bibtex

  @inproceedings{DR:GLOBECOM-03,
    author = {Rossi, D. and Casetti, C. and Mellia, M.},
    title = {User Patience and the Web: a Hands-on Investigation},
    booktitle = {IEEE Globecom'03},
    address = {San Francisco, CA, USA},
    year = {2003},
    month = dec,
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/rossi03globecom.pdf}
  }
  
• [GLOBECOM-02] D.Rossi and C.Casetti and M.Mellia, "A Simulation Study of Web Traffic over DiffServ Networks" IEEE Globecom’02, nov. 2002, Conference Bibtex

  @inproceedings{DR:GLOBECOM-02,
    author = {D.Rossi and C.Casetti and M.Mellia},
    title = {A Simulation Study of Web Traffic over DiffServ Networks},
    booktitle = {IEEE Globecom'02,},
    address = {Taipei, TW,},
    year = {2002},
    month = nov,
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/rossi02globecom.pdf}
  }
  
• [MSC-01] D.Rossi, "A Simulation Study of Web Traffic over DiffServ Networks," nov. 2001, Bibtex

  @mastersthesis{DR:MSC-01,
    author = {D.Rossi},
    title = {A Simulation Study of Web Traffic over DiffServ Networks,},
    school = {Politecnico di Torino},
    booktitle = {M.Sc. Thesis published in the International Archives},
    address = {},
    year = {2001},
    month = nov,
    howpublished = {https://perso.telecom-paristech.fr/drossi/paper/MISSINGURL.pdf}
  }