Nate Mathews

Nate Mathews

PhD Candidate specializing in the application of machine learning and deep learning techniques to address cybersecurity challenges, particularly in network traffic analysis.

SoK: A Critical Evaluation of Efficient Website Fingerprinting Defenses

Published in IEEE Symposium on Security and Privacy (SP), 2023

This paper provides a detailed re-evaluation of nine recent efficient website fingerprinting defenses, particularly focusing on their performance against the latest deep-learning-based attacks. The study explores the feasibility of real-world implementation within the Tor framework and introduces novel attack strategies that reduce the effectiveness of these defenses. Furthermore, this work presents the first on-network implementation of the DynaFlow defense to assess its practical utility. Key findings indicate that TrafficSliver is the most effective defense with reasonable overheads, while Interspace and FRONT offer balanced trade-offs between security and efficiency.

Recommended citation: Nate Mathews, James K. Holland, Se Eun Oh, Mohammad Saidur Rahman, Nicholas Hopper, Matthew Wright. (2023). "SoK: A Critical Evaluation of Efficient Website Fingerprinting Defenses." IEEE Symposium on Security and Privacy (SP), 2023. DOI: 10.1109/SP46215.2023.10179289.
Download Paper | Download Slides