Memory-chasing attack fingerprints websites via DRAM traffic
Original title: Robust & Scalable Website Fingerprinting via Minimal DRAM Traffic
Memory-chasing counts DRAM accesses to achieve 96% accuracy on 24-core systems.
Website fingerprinting attacks infer visited websites using shared system resources. Existing co-located attacks suffer performance degradation on many-core systems. Memory-chasing exploits DRAM traffic interference through pointer-chasing traversals. It achieves 96% accuracy on the top 50 websites on a 24-core system, 86% across multiple CCDs, and 80% across multiple sockets. The attack is robust across hardware configurations, browsers, operating systems, and countermeasures.
- 96% accuracy on 24-core system for top 50 websites
- 86% accuracy across multiple CCDs
- 80% accuracy across multiple sockets
- 97% in open-world setting
From the original article
1 min read at arxiv.orgWebsite fingerprinting attacks infer websites visited by users and threaten their privacy. These attacks are classified as on-path, which monitor network traffic, and co-located, which exploit shared system resources. Existing co-located attacks, such as sweep-counting and loop-counting, achieve over 90% accuracy but suffer significant performance degradation on many-core systems.
By Shubham Roy · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.