skip to main content

Title: Adversarial Traces for Website Fingerprinting Defense
Website Fingerprinting (WF) is a traffic analysis attack that enables an eavesdropper to infer the victim's web activity even when encrypted and even when using the Tor anonymity system. Using deep learning classifiers, the attack can reach up to 98% accuracy. Existing WF defenses are either too expensive in terms of bandwidth and latency overheads (e.g. 2-3 times as large or slow) or ineffective against the latest attacks. In this work, we explore a novel defense based on the idea of adversarial examples that have been shown to undermine machine learning classifiers in other domains. Our Adversarial Traces defense adds padding to a Tor traffic trace in a manner that reliably fools the classifier into classifying it as coming from a different site. The technique drops the accuracy of the state-of-the-art attack from 98% to 60%, while incurring a reasonable 47% bandwidth overhead, showing its promise as a possible defense for Tor.
; ;
Award ID(s):
Publication Date:
Journal Name:
Proceedings of the 2018 ACM SIGSAC Conference on Computer and Communications Security
Page Range or eLocation-ID:
2225 to 2227
Sponsoring Org:
National Science Foundation
More Like this
  1. Abstract Website Fingerprinting (WF) attacks are used by local passive attackers to determine the destination of encrypted internet traffic by comparing the sequences of packets sent to and received by the user to a previously recorded data set. As a result, WF attacks are of particular concern to privacy-enhancing technologies such as Tor. In response, a variety of WF defenses have been developed, though they tend to incur high bandwidth and latency overhead or require additional infrastructure, thus making them difficult to implement in practice. Some lighter-weight defenses have been presented as well; still, they attain only moderate effectiveness against recently published WF attacks. In this paper, we aim to present a realistic and novel defense, RegulaTor, which takes advantage of common patterns in web browsing traffic to reduce both defense overhead and the accuracy of current WF attacks. In the closed-world setting, RegulaTor reduces the accuracy of the state-of-the-art attack, Tik-Tok, against comparable defenses from 66% to 25.4%. To achieve this performance, it requires 6.6% latency overhead and a bandwidth overhead 39.3% less than the leading moderate-overhead defense. In the open-world setting, RegulaTor limits a precision-tuned Tik-Tok attack to an F 1 -score of. 135, compared to .625 formore »the best comparable defense.« less
  2. Abstract A passive local eavesdropper can leverage Website Fingerprinting (WF) to deanonymize the web browsing activity of Tor users. The value of timing information to WF has often been discounted in recent works due to the volatility of low-level timing information. In this paper, we more carefully examine the extent to which packet timing can be used to facilitate WF attacks. We first propose a new set of timing-related features based on burst-level characteristics to further identify more ways that timing patterns could be used by classifiers to identify sites. Then we evaluate the effectiveness of both raw timing and directional timing which is a combination of raw timing and direction in a deep-learning-based WF attack. Our closed-world evaluation shows that directional timing performs best in most of the settings we explored, achieving: (i) 98.4% in undefended Tor traffic; (ii) 93.5% on WTF-PAD traffic, several points higher than when only directional information is used; and (iii) 64.7% against onion sites, 12% higher than using only direction. Further evaluations in the open-world setting show small increases in both precision (+2%) and recall (+6%) with directional-timing on WTF-PAD traffic. To further investigate the value of timing information, we perform an information leakagemore »analysis on our proposed handcrafted features. Our results show that while timing features leak less information than directional features, the information contained in each feature is mutually exclusive to one another and can thus improve the robustness of a classifier.« less
  3. Website Fingerprinting (WF) attacks pose a serious threat to users' online privacy, including for users of the Tor anonymity system. By exploiting recent advances in deep learning, WF attacks like Deep Fingerprinting (DF) have reached up to 98% accuracy. The DF attack, however, requires large amounts of training data that needs to be updated regularly, making it less practical for the weaker attacker model typically assumed in WF. Moreover, research on WF attacks has been criticized for not demonstrating attack effectiveness under more realistic and more challenging scenarios. Most research on WF attacks assumes that the testing and training data have similar distributions and are collected from the same type of network at about the same time. In this paper, we examine how an attacker could leverage N-shot learning---a machine learning technique requiring just a few training samples to identify a given class---to reduce the effort of gathering and training with a large WF dataset as well as mitigate the adverse effects of dealing with different network conditions. In particular, we propose a new WF attack called Triplet Fingerprinting (TF) that uses triplet networks for N-shot learning. We evaluate this attack in challenging settings such as where the training andmore »testing data are collected multiple years apart on different networks, and we find that the TF attack remains effective in such settings with 85% accuracy or better. We also show that the TF attack is also effective in the open world and outperforms traditional transfer learning. On top of that, the attack requires only five examples to recognize a website, making it dangerous in a wide variety of scenarios where gathering and training on a complete dataset would be impractical.« less
  4. Most privacy-conscious users utilize HTTPS and an anonymity network such as Tor to mask source and destination IP addresses. It has been shown that encrypted and anonymized network traffic traces can still leak information through a type of attack called a website fingerprinting (WF) attack. The adversary records the network traffic and is only able to observe the number of incoming and outgoing messages, the size of each message, and the time difference between messages. In previous work, the effectiveness of website fingerprinting has been shown to have an accuracy of over 90% when using Tor as the anonymity network. Thus, an Internet Service Provider can successfully identify the websites its users are visiting. One main concern about website fingerprinting is its practicality. The common assumption in most previous work is that a victim is visiting one website at a time and has access to the complete network trace of that website. However, this is not realistic. We propose two new algorithms to deal with situations when the victim visits one website after another (continuous visits) and visits another website in the middle of visiting one website (overlapping visits). We show that our algorithm gives an accuracy of 80% (comparedmore »to 63% in a previous work [24]) in finding the split point which is the start point for the second website in a trace. Using our proposed “splitting” algorithm, websites can be predicted with an accuracy of 70%. When two website visits are overlapping, the website fingerprinting accuracy falls dramatically. Using our proposed “sectioning” algorithm, the accuracy for predicting the website in overlapping visits improves from 22.80% to 70%. When part of the network trace is missing (either the beginning or the end), the accuracy when using our sectioning algorithm increases from 20% to over 60%.« less
  5. Website fingerprinting attacks, which use statistical analysis on network traffic to compromise user privacy, have been shown to be effective even if the traffic is sent over anonymity-preserving networks such as Tor. The classical attack model used to evaluate website fingerprinting attacks assumes an on-path adversary, who can observe all traffic traveling between the user’s computer and the secure network. In this work we investigate these attacks under a different attack model, in which the adversary is capable of sending a small amount of malicious JavaScript code to the target user’s computer. The malicious code mounts a cache side-channel attack, which exploits the effects of contention on the CPU’s cache, to identify other websites being browsed. The effectiveness of this attack scenario has never been systematically analyzed, especially in the open-world model which assumes that the user is visiting a mix of both sensitive and non-sensitive sites. We show that cache website fingerprinting attacks in JavaScript are highly feasible. Specifically, we use machine learning techniques to classify traces of cache activity. Unlike prior works, which try to identify cache conflicts, our work measures the overall occupancy of the last-level cache. We show that our approach achieves high classification accuracy inmore »both the open-world and the closed-world models. We further show that our attack is more resistant than network-based fingerprinting to the effects of response caching, and that our techniques are resilient both to network-based defenses and to side-channel countermeasures introduced to modern browsers as a response to the Spectre attack. To protect against cache-based website fingerprinting, new defense mechanisms must be introduced to privacy-sensitive browsers and websites. We investigate one such mechanism, and show that generating artificial cache activity reduces the effectiveness of the attack and completely eliminates it when used in the Tor Browser« less