Automated Website Fingerprinting through Deep Learning

By Vera Rimmer, Davy Preuveneers, Marc Juárez, Tom van Goethem, Wouter Joosen. Network and Distributed System Security Symposium, 2017

419 citations recorded by the source corpus.

Several studies have shown that the network traffic that is generated by a visit to a website over Tor reveals information specific to the website through the timing and sizes of network packets. By capturing traffic traces between users and their Tor entry guard, a network eavesdropper can leverage this meta-data to reveal which website Tor users are visiting. The success of such attacks heavily depends on the particular set of traffic features that are used to construct the fingerprint. Typically, these features are manually engineered and, as such, any change introduced to the Tor network can render these carefully constructed features ineffective. In this paper, we show that an adversary can automate the feature engineering process, and thus automatically deanonymize Tor traffic by applying our novel method based on deep learning. We evaluate our approach on a dataset comprised of more than three million network traces, which is the largest dataset of web traffic ever gathered for website fingerprinting, and find that the performance achieved by deep learning techniques is comparable to known approaches which include various research efforts spanning over multiple years. Furthermore, it eliminates the need for feature design and selection which is a tedious work and has been one of the main focus of prior work. We conclude that the ability to automatically construct the most relevant traffic features and perform accurate traffic recognition makes our deep learning based approach an efficient, flexible and robust technique for website fingerprinting.

Subfields: Artificial Intelligence, Computer Networks and Communications

View Paper: https://www.semanticscholar.org/paper/9084735e7d0bff1949c2a1c59b2bfa9f8baa82b8

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Networks and Communications

Citations in the corpus

Tranco: A Research-Oriented Top Sites Ranking Hardened Against Manipulation (2018, background): “for evaluating Tor fingerprinting [61]; whitelist if the lists are seen as a source of benign websites, e.”
Accurate Decentralized Application Identification via Encrypted Traffic Analysis Using Graph Neural Networks (2021, methodology): “Recent studies attempted to use deep neural networks, such as Convolutional Neural Networks (CNNs) [18], [19], [26] and Long-Short Term Memory (LSTM) [19] to construct more accurate fingerprints.”
Packet Chasing: Spying on Network Packets over a Cache Side-Channel (2019, neutral): “For example, the results in [76] suggests that using only the network packet sizes and their timing information (the exact information that Packet Chasing can obtain) can be enough to build a classifier with up to 95% accuracy.”
Deep Fingerprinting: Undermining Website Fingerprinting Defenses with Deep Learning (2018, methodology): “Following the experimental procedures of Rimmer et al. [31] and Panchenko et al. [27], we focus on the binary results of whether the input trace is classified as monitored (predicted to be in any of the monitored classes) or un-monitored.”