Microarchitectural attacks have become more threatening the hardware security than before with the increasing diversity of attacks such as Spectre and Meltdown. Vendor patches cannot keep up with the pace of the new threats, which makes the dynamic anomaly detection tools more evident than before. Unfortunately, previous studies utilize hardware performance counters that lead to high performance overhead and profile limited number of microarchitectural attacks due to the small number of counters that can be profiled concurrently. This yields those detection tools inefficient in real-world scenarios. In this study, we introduce MAD-EN dynamic detection tool that leverages system-wide energy consumption traces collected from a generic Intel RAPL tool to detect ongoing anomalies in a system. In our experiments, we show that CNN-based MAD-EN can detect 10 different microarchitectural attacks with a total of 15 variants with the highest F1 score of 0.999, which makes our tool the most generic attack detection tool so far. Moreover, individual attacks can be distinguished with a 98% accuracy after an anomaly is detected in a system. We demonstrate that MAD-EN introduces 69.3% less performance overhead compared to performance counter-based detection mechanisms.
翻译:微分构造攻击比以往更威胁到硬件安全。 供应商补丁无法跟上新威胁的步伐, 这使得动态异常探测工具比以前更加明显。 不幸的是, 以前的研究利用硬件性能计数器导致高性能管理, 微分构造攻击数量有限, 这是因为可以同时剖析的计数器数量少, 使得这些探测工具在现实世界情景中效率低下。 在这项研究中, 我们引入了MAD- EN动态探测工具, 利用从普通 Intel RAPL 工具收集的全系统能源消耗痕迹来探测系统内的持续异常。 在我们的实验中, 我们显示CNN的MAD-EN 能够探测出十次不同的微分微分仪攻击, 总共15个变量, F1 得分最高, 0. 999, 这使我们的工具成为迄今为止最通用的攻击探测工具。 此外, 在系统检测出异常之后, 个人攻击可以辨别出98%的准确度。 我们证明, MAD- EN 输入了69.3%的性能比反向反向检测机制低69.3% 。