DeepSE-WF: Unified Security Estimation for Website Fingerprinting Defenses

Abstract

Website fingerprinting (WF) attacks, usually conducted with the help of a machine learning-based classifier, enable a network eavesdropper to pinpoint which website a user is accessing through the inspection of traffic patterns. These attacks have been shown to succeed even when users browse the Internet through encrypted tunnels, e.g., through Tor or VPNs. To assess the security of new defenses against WF attacks, recent works have proposed feature-dependent theoretical frameworks that estimate the Bayes error of an adversary's features set or the mutual information leaked by manually-crafted features. Unfortunately, as WF attacks increasingly rely on deep learning and latent feature spaces, our experiments show that security estimations based on simpler (and less informative) manually-crafted features can no longer be trusted to assess the potential success of a WF adversary in defeating such defenses. In this work, we propose DeepSE-WF, a novel WF security estimation framework that leverages specialized kNN-based estimators to produce Bayes error and mutual information estimates from learned latent feature spaces, thus bridging the gap between current WF attacks and security estimation methods. Our evaluation reveals that DeepSE-WF produces tighter security estimates than previous frameworks, reducing the required computational resources to output security estimations by one order of magnitude.

A First Look at Generating Website Fingerprinting Attacks via Neural Architecture Search

“…Defense configurations. We follow the methodology of Veicht et al [44] and use default parameters for WF defenses, as suggested in their original papers. We used the WTF-PAD implementation from the WFES repository [5], and two versions of FRONT [14] with parameters: 𝑁 𝑐 = 𝑁 𝑠 = 1700 and 𝑊 𝑚𝑖𝑛 = 1, 𝑊 𝑚𝑎𝑥 = 14 for FRONT_T1, and 𝑁 𝑐 = 𝑁 𝑠 = 2500 for FRONT_T2.…”

“…Inspired by Veicht et al [44], we assess the effectiveness of Tik-Tok and AutoKeras-generated models on a set of relevant WF defenses which are accompanied by high-fidelity simulators [15]. We use these simulators to generate defended traffic from the prerecorded undefended traces contained in the DS-19 dataset.…”

Connecting the Dots in the Sky: Website Fingerprinting in Low Earth Orbit Satellite Internet

“…Gong et al [10] have recently compared the simulation and true implementation results for a set of WF defenses and reached the conclusion that simulators can accurately reflect the effectiveness of defenses on live traffic. We utilize the same defense simulators and configurations recently used in the work of Veicht et al [45], which focused on the security analysis of website fingerprinting defenses. We refer the reader to Appendix B for details on the defenses' parameters.…”