Search

Stateful and stateless web tracking gathered much attention in the last decade, however they were always measured separately. To the best of our knowledge, our study is the first to detect and measure cookie respawning with browser and machine fingerprinting. We develop a detection methodology that allows us to detect cookies dependency on browser and machine features. Our results show that 1,150 out of the top 30, 000 Alexa websites deploy this tracking mechanism. We further uncover how domains collaborate to respawn cookies through fingerprinting. We find out that this technique can be used to track users across websites even when third-party cookies are deprecated. Together with a legal scholar, we conclude that cookie respawning with browser fingerprinting lacks legal interpretation under the GDPR and the ePrivacy directive, but its use in practice may breach them, thus subjecting it to fines up to 20 million euro.

Web tracking has been extensively studied over the last decade. To detect tracking, previous studies and user tools rely on filter lists. However, it has been shown that filter lists miss trackers. In this paper, we propose an alternative method to detect trackers inspired by analyzing behavior of invisible pixels. By crawling 84,658 webpages from 8,744 domains, we detect that third-party invisible pixels are widely deployed: they are present on more than 94.51% of domains and constitute 35.66% of all third-party images. We propose a fine-grained behavioral classification of tracking based on the analysis of invisible pixels. We use this classification to detect new categories of tracking and uncover new collaborations between domains on the full dataset of 4,216,454 third-party requests. We demonstrate that two popular methods to detect tracking, based on EasyList&EasyPrivacy and on Disconnect lists respectively miss 25.22% and 30.34% of the trackers that we detect. Moreover, we find that if we combine all three lists 379,245 requests originated from 8,744 domains still track users on 68.70% of websites., Comment: This paper has been accepted to PETs 2020

It is well known that apps running on mobile devices extensively track and leak users' personally identifiable information (PII); however, these users have little visibility into PII leaked through the network traffic generated by their devices, and have poor control over how, when and where that traffic is sent and handled by third parties. In this paper, we present the design, implementation, and evaluation of ReCon: a cross-platform system that reveals PII leaks and gives users control over them without requiring any special privileges or custom OSes. ReCon leverages machine learning to reveal potential PII leaks by inspecting network traffic, and provides a visualization tool to empower users with the ability to control these leaks via blocking or substitution of PII. We evaluate ReCon's effectiveness with measurements from controlled experiments using leaks from the 100 most popular iOS, Android, and Windows Phone apps, and via an IRB-approved user study with 92 participants. We show that ReCon is accurate, efficient, and identifies a wider range of PII than previous approaches., Comment: Please use MobiSys version when referencing this work: http://dl.acm.org/citation.cfm?id=2906392. 18 pages, recon.meddle.mobi

Twitter is one of the largest social networks using exclusively directed links among accounts. This makes the Twitter social graph much closer to the social graph supporting real life communications than, for instance, Facebook. Therefore, understanding the structure of the Twitter social graph is interesting not only for computer scientists, but also for researchers in other fields, such as sociologists. However, little is known about how the information propagation in Twitter is constrained by its inner structure. In this paper, we present an in-depth study of the macroscopic structure of the Twitter social graph unveiling the highways on which tweets propagate, the specific user activity associated with each component of this macroscopic structure, and the evolution of this macroscopic structure with time for the past 6 years. For this study, we crawled Twitter to retrieve all accounts and all social relationships (follow links) among accounts; the crawl completed in July 2012 with 505 million accounts interconnected by 23 billion links. Then, we present a methodology to unveil the macroscopic structure of the Twitter social graph. This macroscopic structure consists of 8 components defined by their connectivity characteristics. Each component group users with a specific usage of Twitter. For instance, we identified components gathering together spammers, or celebrities. Finally, we present a method to approximate the macroscopic structure of the Twitter social graph in the past, validate this method using old datasets, and discuss the evolution of the macroscopic structure of the Twitter social graph during the past 6 years., Comment: ACM Sigmetrics 2014 (2014)

In this paper, we consider how to maximize users' influence in Online Social Networks (OSNs) by exploiting social relationships only. Our first contribution is to extend to OSNs the model of Kempe et al. [1] on the propagation of information in a social network and to show that a greedy algorithm is a good approximation of the optimal algorithm that is NP-hard. However, the greedy algorithm requires global knowledge, which is hardly practical. Our second contribution is to show on simulations on the full Twitter social graph that simple and practical strategies perform close to the greedy algorithm., Comment: NetSciCom 2014 - The Sixth IEEE International Workshop on Network Science for Communication Networks (2014)

Video streaming represents a large fraction of Internet traffic. Surprisingly, little is known about the network characteristics of this traffic. In this paper, we study the network characteristics of the two most popular video streaming services, Netflix and YouTube. We show that the streaming strategies vary with the type of the application (Web browser or native mobile application), and the type of container (Silverlight, Flash, or HTML5) used for video streaming. In particular, we identify three different streaming strategies that produce traffic patterns from non-ack clocked ON-OFF cycles to bulk TCP transfer. We then present an analytical model to study the potential impact of these streaming strategies on the aggregate traffic and make recommendations accordingly., Comment: This is the author version of the paper accepted as a full paper at ACM CoNEXT 2011

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. Experiments 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 careful mixtures of TCP and uTP traffic., Comment: 14 pages, under submission

In this paper, we show how to exploit real-time communication applications to determine the IP address of a targeted user. We focus our study on Skype, although other real-time communication applications may have similar privacy issues. We first design a scheme that calls an identified targeted user inconspicuously to find his IP address, which can be done even if he is behind a NAT. By calling the user periodically, we can then observe the mobility of the user. We show how to scale the scheme to observe the mobility patterns of tens of thousands of users. We also consider the linkability threat, in which the identified user is linked to his Internet usage. We illustrate this threat by combining Skype and BitTorrent to show that it is possible to determine the file-sharing usage of identified users. We devise a scheme based on the identification field of the IP datagrams to verify with high accuracy whether the identified user is participating in specific torrents. We conclude that any Internet user can leverage Skype, and potentially other real-time communication systems, to observe the mobility and file-sharing usage of tens of millions of identified users., Comment: This is the authors' version of the ACM/USENIX Internet Measurement Conference (IMC) 2011 paper

Tor is a popular low-latency anonymity network. However, Tor does not protect against the exploitation of an insecure application to reveal the IP address of, or trace, a TCP stream. In addition, because of the linkability of Tor streams sent together over a single circuit, tracing one stream sent over a circuit traces them all. Surprisingly, it is unknown whether this linkability allows in practice to trace a significant number of streams originating from secure (i.e., proxied) applications. In this paper, we show that linkability allows us to trace 193% of additional streams, including 27% of HTTP streams possibly originating from "secure" browsers. In particular, we traced 9% of Tor streams carried by our instrumented exit nodes. Using BitTorrent as the insecure application, we design two attacks tracing BitTorrent users on Tor. We run these attacks in the wild for 23 days and reveal 10,000 IP addresses of Tor users. Using these IP addresses, we then profile not only the BitTorrent downloads but also the websites visited per country of origin of Tor users. We show that BitTorrent users on Tor are over-represented in some countries as compared to BitTorrent users outside of Tor. By analyzing the type of content downloaded, we then explain the observed behaviors by the higher concentration of pornographic content downloaded at the scale of a country. Finally, we present results suggesting the existence of an underground BitTorrent ecosystem on Tor.

This paper studies the economic utilities and the quality of service (QoS) in a two-sided non-neutral market where Internet service providers (ISPs) charge content providers (CPs) for the content delivery. We propose new models on a two-sided market which involves a CP, an ISP, end users and advertisers. The CP may have either the subscription revenue model (charging end users) or the advertisement revenue model (charging advertisers). We formulate the interactions between the ISP and the CP as a noncooperative game problem for the former and an optimization problem for the latter. Our analysis shows that the revenue model of the CP plays a significant role in a non-neutral Internet. With the subscription model, both the ISP and the CP receive better (or worse) utilities as well as QoS in the presence of side payment at the same time. However, with the advertisement model, the side payment impedes the CP from investing on its contents., Comment: 15 pages, 10 figures

Peer-to-peer (P2P) locality has recently raised a lot of interest in the community. Indeed, whereas P2P content distribution enables financial savings for the content providers, it dramatically increases the traffic on inter-ISP links. To solve this issue, the idea to keep a fraction of the P2P traffic local to each ISP was introduced a few years ago. Since then, P2P solutions exploiting locality have been introduced. However, several fundamental issues on locality still need to be explored. In particular, how far can we push locality, and what is, at the scale of the Internet, the reduction of traffic that can be achieved with locality? In this paper, we perform extensive experiments on a controlled environment with up to 10,000 BitTorrent clients to evaluate the impact of high locality on inter-ISP links traffic and peers download completion time. We introduce two simple mechanisms that make high locality possible in challenging scenarios and we show that we save up to several orders of magnitude inter-ISP traffic compared to traditional locality without adversely impacting peers download completion time. In addition, we crawled 214,443 torrents representing 6,113,224 unique peers spread among 9,605 ASes. We show that whereas the torrents we crawled generated 11.6 petabytes of inter-ISP traffic, our locality policy implemented for all torrents could have reduced the global inter-ISP traffic by up to 40%.

Network latency and packet loss are considered to be an important requirement for realistic evaluation of Peer-to-Peer protocols. Dedicated clusters, such as Grid'5000, do not provide the variety of network latency and packet loss rates that can be found in the Internet. However, compared to the experiments performed on testbeds such as PlanetLab, the experiments performed on dedicated clusters are reproducible, as the computational resources are not shared. In this paper, we perform experiments to study the impact of network latency and packet loss on the time required to download a file using BitTorrent. In our experiments, we observe a less than 15% increase on the time required to download a file when we increase the round-trip time between any two peers, from 0 ms to 400 ms, and the packet loss rate, from 0% to 5%. Our main conclusion is that the underlying network latency and packet loss have a marginal impact on the time required to download a file using BitTorrent. Hence, dedicated clusters such as Grid'5000 can be safely used to perform realistic and reproducible BitTorrent experiments.

Privacy of users in P2P networks goes far beyond their current usage and is a fundamental requirement to the adoption of P2P protocols for legal usage. In a climate of cold war between these users and anti-piracy groups, more and more users are moving to anonymizing networks in an attempt to hide their identity. However, when not designed to protect users information, a P2P protocol would leak information that may compromise the identity of its users. In this paper, we first present three attacks targeting BitTorrent users on top of Tor that reveal their real IP addresses. In a second step, we analyze the Tor usage by BitTorrent users and compare it to its usage outside of Tor. Finally, we depict the risks induced by this de-anonymization and show that users' privacy violation goes beyond BitTorrent traffic and contaminates other protocols such as HTTP.

Some BitTorrent users are running BitTorrent on top of Tor to preserve their privacy. In this extended abstract, we discuss three different attacks to reveal the IP address of BitTorrent users on top of Tor. In addition, we exploit the multiplexing of streams from different applications into the same circuit to link non-BitTorrent applications to revealed IP addresses., Comment: Poster accepted at the 7th USENIX Symposium on Network Design and Implementation (NSDI '10), San Jose, CA : United States (2010)

This paper presents a set of exploits an adversary can use to continuously spy on most BitTorrent users of the Internet from a single machine and for a long period of time. Using these exploits for a period of 103 days, we collected 148 million IPs downloading 2 billion copies of contents. We identify the IP address of the content providers for 70% of the BitTorrent contents we spied on. We show that a few content providers inject most contents into BitTorrent and that those content providers are located in foreign data centers. We also show that an adversary can compromise the privacy of any peer in BitTorrent and identify the big downloaders that we define as the peers who subscribe to a large number of contents. This infringement on users' privacy poses a significant impediment to the legal adoption of BitTorrent.

In this paper, we study the impact of network latency on the time required to download a file distributed using BitTorrent. This study is essential to understand if testbeds can be used for experimental evaluation of BitTorrent. We observe that the network latency has a marginal impact on the time required to download a file; hence, BitTorrent experiments can performed on testbeds.

Swarming peer-to-peer systems play an increasingly instrumental role in Internet content distribution. It is therefore important to better understand how these systems behave in practice. Recent research efforts have looked at various protocol parameters and have measured how they affect system performance and robustness. However, the importance of the strategy based on which peers establish connections has been largely overlooked. This work utilizes extensive simulations to examine the default overlay construction strategy in BitTorrent systems. Based on the results, we identify a critical parameter, the maximum allowable number of outgoing connections at each peer, and evaluate its impact on the robustness of the generated overlay. We find that there is no single optimal value for this parameter using the default strategy. We then propose an alternative strategy that allows certain new peer connection requests to replace existing connections. Further experiments with the new strategy demonstrate that it outperforms the default one for all considered metrics by creating an overlay more robust to churn. Additionally, our proposed strategy exhibits optimal behavior for a well-defined value of the maximum number of outgoing connections, thereby removing the need to set this parameter in an ad-hoc manner.

Peer-to-peer (P2P) locality has recently raised a lot of interest in the community. Indeed, whereas P2P content distribution enables financial savings for the content providers, it dramatically increases the traffic on inter-ISP links. To solve this issue, the idea to keep a fraction of the P2P traffic local to each ISP was introduced a few years ago. Since then, P2P solutions exploiting locality have been introduced. However, several fundamental issues on locality still need to be explored. In particular, how far can we push locality, and what is, at the scale of the Internet, the reduction of traffic that can be achieved with locality? In this paper, we perform extensive experiments on a controlled environment with up to 10 000 BitTorrent clients to evaluate the impact of high locality on inter-ISP links traffic and peers download completion time. We introduce two simple mechanisms that make high locality possible in challenging scenarios and we show that we save up to several orders of magnitude inter-ISP traffic compared to traditional locality without adversely impacting peers download completion time. In addition, we crawled 214 443 torrents representing 6 113 224 unique peers spread among 9 605 ASes. We show that whereas the torrents we crawled generated 11.6 petabytes of inter-ISP traffic, our locality policy implemented for all torrents would have reduced the global inter-ISP traffic by 40%.

Peer-to-peer content distribution systems have been enjoying great popularity, and are now gaining momentum as a means of disseminating video streams over the Internet. In many of these protocols, including the popular BitTorrent, content is split into mostly fixed-size pieces, allowing a client to download data from many peers simultaneously. This makes piece size potentially critical for performance. However, previous research efforts have largely overlooked this parameter, opting to focus on others instead. This paper presents the results of real experiments with varying piece sizes on a controlled BitTorrent testbed. We demonstrate that this parameter is indeed critical, as it determines the degree of parallelism in the system, and we investigate optimal piece sizes for distributing small and large content. We also pinpoint a related design trade-off, and explain how BitTorrent's choice of dividing pieces into subpieces attempts to address it.

In this paper, we conduct extensive simulations to understand the properties of the overlay generated by BitTorrent. We start by analyzing how the overlay properties impact the efficiency of BitTorrent. We focus on the average peer set size (i.e., average number of neighbors), the time for a peer to reach its maximum peer set size, and the diameter of the overlay. In particular, we show that the later a peer arrives in a torrent, the longer it takes to reach its maximum peer set size. Then, we evaluate the impact of the maximum peer set size, the maximum number of outgoing connections per peer, and the number of NATed peers on the overlay properties. We show that BitTorrent generates a robust overlay, but that this overlay is not a random graph. In particular, the connectivity of a peer to its neighbors depends on its arriving order in the torrent. We also show that a large number of NATed peers significantly compromise the robustness of the overlay to attacks. Finally, we evaluate the impact of peer exchange on the overlay properties, and we show that it generates a chain-like overlay with a large diameter, which will adversely impact the efficiency of large torrents.

Peer-to-peer protocols play an increasingly instrumental role in Internet content distribution. It is therefore important to gain a complete understanding of how these protocols behave in practice and how their operating parameters affect overall system performance. This paper presents the first detailed experimental investigation of the peer selection strategy in the popular BitTorrent protocol. By observing more than 40 nodes in instrumented private torrents, we validate three protocol properties that, though believed to hold, have not been previously demonstrated experimentally: the clustering of similar-bandwidth peers, the effectiveness of BitTorrent's sharing incentives, and the peers' high uplink utilization. In addition, we observe that BitTorrent's modified choking algorithm in seed state provides uniform service to all peers, and that an underprovisioned initial seed leads to absence of peer clustering and less effective sharing incentives. Based on our results, we provide guidelines for seed provisioning by content providers, and discuss a tracker protocol extension that addresses an identified limitation of the protocol., Comment: This article is the author version of a paper accepted at ACM SIGMETRICS'2007. In particular, this paper is different from the technical report inria-00112066, version 1 - 21 November 2006. The technical report inria-00112066, version 1 - 21 November 2006 is a extended version of this paper (same title and authors, but different content) Version 2 is the same content as version 1, but with a different class in order to match the camera ready format for SIGMETRICS

Peer-to-peer protocols play an increasingly instrumental role in Internet content distribution. Consequently, it is important to gain a full understanding of how these protocols behave in practice and how their parameters impact overall performance. We present the first experimental investigation of the peer selection strategy of the popular BitTorrent protocol in an instrumented private torrent. By observing the decisions of more than 40 nodes, we validate three BitTorrent properties that, though widely believed to hold, have not been demonstrated experimentally. These include the clustering of similar-bandwidth peers, the effectiveness of BitTorrent's sharing incentives, and the peers' high average upload utilization. In addition, our results show that BitTorrent's new choking algorithm in seed state provides uniform service to all peers, and that an underprovisioned initial seed leads to the absence of peer clustering and less effective sharing incentives. Based on our observations, we provide guidelines for seed provisioning by content providers, and discuss a tracker protocol extension that addresses an identified limitation of the protocol.

The performance of peer-to-peer file replication comes from its piece and peer selection strategies. Two such strategies have been introduced by the BitTorrent protocol: the rarest first and choke algorithms. Whereas it is commonly admitted that BitTorrent performs well, recent studies have proposed the replacement of the rarest first and choke algorithms in order to improve efficiency and fairness. In this paper, we use results from real experiments to advocate that the replacement of the rarest first and choke algorithms cannot be justified in the context of peer-to-peer file replication in the Internet. We instrumented a BitTorrent client and ran experiments on real torrents with different characteristics. Our experimental evaluation is peer oriented, instead of tracker oriented, which allows us to get detailed information on all exchanged messages and protocol events. We go beyond the mere observation of the good efficiency of both algorithms. We show that the rarest first algorithm guarantees close to ideal diversity of the pieces among peers. In particular, on our experiments, replacing the rarest first algorithm with source or network coding solutions cannot be justified. We also show that the choke algorithm in its latest version fosters reciprocation and is robust to free riders. In particular, the choke algorithm is fair and its replacement with a bit level tit-for-tat solution is not appropriate. Finally, we identify new areas of improvements for efficient peer-to-peer file replication protocols.