TL;DR
This paper demonstrates that deep learning can automatically extract features from network traffic to accurately identify visited websites over Tor, outperforming traditional manual feature engineering methods.
Contribution
The authors introduce a novel deep learning approach for website fingerprinting that automates feature extraction, achieving high accuracy and robustness against web content changes.
Findings
Over 96% accuracy in closed-world scenarios with 100 websites
94% accuracy in larger closed-world of 900 websites
Deep learning features are more resilient to web content dynamics
Abstract
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 collect a dataset comprised of more than three…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
