Real-Time Detection on Cache Side Channel Attacks using Performance Counter Monitor
Jonghyeon Cho, TaeHyun Kim, Taehun Kim, Youngjoo Shin · 2019
Cache side-channel attack extracts secret information by monitoring cache behavior of a victim. Normally, this attack targets a L3 cache which is shared between a spy and a victim. Hence, spy can learn about secret information without perception of the victim. To resist against this attack, many detection techniques have been proposed in the literature. However, those approaches have limitation since they do not operate in real time. In this paper, we propose a realtime detection technique against cache side-channel attacks. The proposed technique performs detection of cache side-channel attacks immediately after observing variation of CPU counters. For this, Intel PCM (Performance Counter Monitor) and machine learning algorithms are used to measure the value of CPU counters. Throughout the experiment, we found several PCM counters that show changes during the attack. Based on the observation, we implemented a detecting program by using these counters. Experimental results show that the proposed detection technique has good performance for real time detection in various environments.