DefWeb: Defending User Privacy against Cache-based Website Fingerprinting Attacks with Intelligent Noise Injection
Published in Proceedings of the 39th Annual Computer Security Applications Conference (ACSAC '23), 2023
Website fingerprinting attacks allow adversaries to infer which websites a victim is visiting by monitoring shared microarchitectural resources such as CPU caches. DefWeb counters these attacks by injecting intelligent, adaptive noise into the cache access patterns observable to an attacker. Our evaluation shows that DefWeb significantly degrades the accuracy of state-of-the-art machine learning fingerprinting classifiers while imposing minimal performance overhead on end users.
Recommended citation: S. Son, D. R. Dipta and B. Gulmezoglu, "DefWeb: Defending User Privacy against Cache-based Website Fingerprinting Attacks with Intelligent Noise Injection," Proceedings of the 39th Annual Computer Security Applications Conference (ACSAC '23), Association for Computing Machinery, New York, NY, USA, 379–393, 2023.
Download Paper