HidFix: Efficient Mitigation of Cache-Based Spectre Attacks Through Hidden Rollbacks
Arash Pashrashid, Ali Hajiabadi, Trevor E. Carlson · 2023
Mitigating Spectre attacks in modern systems is a challenging task for CPU vendors as they need to provide comprehensive protection while maintaining high efficiency. One common solution is to adopt always-on mitigation strategies to prevent all speculative data leaks. However, these solutions incur prohibitive performance overheads as they limit the benefits of speculative execution, the main performance enabler of modern processors. Additionally, recent attacks have demonstrated the limitations of many existing defenses. Combining side-channel attack (SCA) detectors with mitigation strategies is a promising direction to achieve efficient and selective mitigation of Spectre attacks. In this work, we enumerate the combinations of state-of-the-art detection and mitigation strategies and present both new attacks as well as the potential risks of such detection/mitigation combinations. The result is the HIDFIX methodology, an efficient mitigation for cache-based Spectre attacks, that addresses the security limitations of prior work. We show that Hidfix has a near-zero performance overhead for all evaluated applications. Hidfix rollbacks the misspeculated data leaks in a timely manner, before an attacker has the chance to infer the victim's sensitive data. We demonstrate that HidFix is more secure compared to prior cache-based Spectre defenses, and moreover, it does not introduce new side effects that might enable an attacker to observe secret dependent changes in the system.