[论文解读] FortuneTeller: Predicting Microarchitectural Attacks via Unsupervised Deep Learning

Berk Gülmezoğlu, Daniel Moghimi+2 more|arXiv (Cornell University)|Jul 8, 2019

Security and Verification in Computing参考文献 62被引用 34

一句话总结

FortuneTeller 使用未经监督的 RNN（LSTM/GRU），在良性硬件性能计数器上训练，以实时检测未见过的微架构攻击，在没有带标签的训练数据的情况下实现高 F 分数和广泛的攻击覆盖。

ABSTRACT

The growing security threat of microarchitectural attacks underlines the importance of robust security sensors and detection mechanisms at the hardware level. While there are studies on runtime detection of cache attacks, a generic model to consider the broad range of existing and future attacks is missing. Unfortunately, previous approaches only consider either a single attack variant, e.g. Prime+Probe, or specific victim applications such as cryptographic implementations. Furthermore, the state-of-the art anomaly detection methods are based on coarse-grained statistical models, which are not successful to detect anomalies in a large-scale real world systems. Thanks to the memory capability of advanced Recurrent Neural Networks (RNNs) algorithms, both short and long term dependencies can be learned more accurately. Therefore, we propose FortuneTeller, which for the first time leverages the superiority of RNNs to learn complex execution patterns and detects unseen microarchitectural attacks in real world systems. FortuneTeller models benign workload pattern from a microarchitectural standpoint in an unsupervised fashion, and then, it predicts how upcoming benign executions are supposed to behave. Potential attacks and malicious behaviors will be detected automatically, when there is a discrepancy between the predicted execution pattern and the runtime observation. We implement FortuneTeller based on the available hardware performance counters on Intel processors and it is trained with 10 million samples obtained from benign applications. For the first time, the latest attacks such as Meltdown, Spectre, Rowhammer and Zombieload are detected with one trained model and without observing these attacks during the training. We show that FortuneTeller achieves F-score of 0.9970.

研究动机与目标

• 使用无监督深度学习对良性微架构行为建模，以检测异常。
• 开发一个通用、与应用无关的检测器，能够识别未见的攻击。
• 利用硬件性能计数器作为实时检测的安全传感器。

提出的方法

• 在良性执行期间从核心 HPC 收集时间序列数据。
• 使用滑动窗口训练 LSTM 和 GRU 模型，以预测下一个计数值（自监督）。
• 通过将预测值与实时测量值进行比较，在检测窗口上应用阈值来检测异常。
• 对计数器进行分析并选择一个最优子集，以最大化检测性能。
• 在良性工作负载以及一组已知和新颖的微架构攻击上进行评估。

实验结果

研究问题

• RQ1 无监督的 RNN 模型是否能够学习良性微架构模式以检测未见的攻击？
• RQ2 计数器选择与窗口大小对检测性能和误警报的影响是什么？
• RQ3 FortuneTeller 在真实服务器和笔记本环境中检测现代攻击的效果如何？
• RQ4 在实时系统中部署 FortuneTeller 的开销是多少？

主要发现

• FortuneTeller 实现了强大的异常检测性能，报告的最高 F-score 为 0.9970。
• 训练使用 1,000 万个良性样本来建模正常行为。
• 三个核心计数器（L1_Inst_Miss、L1_Inst_Hit、LLC_Miss）为多样化攻击提供高检测能力。
• 该方法能够检测诸如 Flush+Flush、Spectre、Meltdown、Zombieload 等隐蔽和短暂攻击，包括未见的变体。
• 一个无监督、以计数器为驱动的模型对目标应用是不可知的，并且可以推广到真实世界的工作负载。