Differential Privacy for Secure Cache Partitioning: Promises, Limits, and Fixes

Abstract

The shared last-level cache (LLC) enables cross-core contention-based attacks. While LLC randomization mitigates conflict-based attacks, cache partitioning prevents all attack classes. Recent secure partitioning techniques dynamically allocate LLC space and claim security against cache occupancy attacks. We show that state-of-the-art LLC usage-based dynamic partitioning remains vulnerable. Focusing on Secure and Scalable Cache Partitioning (SCALE), which applies differential privacy–based noise to LLC way allocations, we demonstrate that allocations can be denoised over time to construct a reliable LLC occupancy channel. The key insight that drives the occupancy channel is that differential privacy protects individual allocations; it does not hide long-term statistics such as the mean, median, and standard deviation. We showcase a novel LLC occupancy attack that does application fingerprint exploiting statistical properties. Finally, we propose lightweight fixes that mitigate this leakage.