Cache-Collision Attacks on GPU-Based AES Implementation with Electro-Magnetic Leakages

Published in TrustCom (17th IEEE International Conference On Trust, Security And Privacy In Computing And Communications), 2018

Citation: Yiwen Gao, Wei Cheng, Hailong Zhang, Yongbin Zhou. Cache-Collision Attacks on GPU-Based AES Implementation with Electro-Magnetic Leakages. TrustCom/BigDataSE 2018 : 300-306. [Online link, Full version, BibTeX]

For computationally-intensive tasks like cryptographic applications, GPU is thought to be an ideal platform due to its parallel computing power. However, some vulnerabilities of GPU have been published due to overflow attacks,covert-channel attacks and side-channel attacks. In this work, for the first time, we investigate cache-collision attacks on GPU-based AES implementation utilizing Electro-Magnetic (EM) leakages. We construct a much efficient leakage model based on generalized simultaneous cache-collision in multi-threads scenarios, and we mount a key-recovery attack with Differential Electro-Magnetic Analysis (DEMA). Our evaluation results show that the 16-byte secret key of GPU-based AES implementation can be recovered with only 5,000 EM traces, and 600 EM traces are enough when assisted with appropriate key enumeration algorithm (KEA). This work suggests that cache-collision on GPU does give rise to leakages via EM side-channels and it should be considered in the design of secure GPU-based cryptographic implementations.