Monotonic-HMDs: Exploiting Monotonic Features to Defend Against Evasive Malware
Monotonic-HMDs: Exploiting Monotonic Features to Defend Against Evasive Malware
复制标题
单调头戴式显示器：利用单调特征防御规避恶意软件
DOI：
--
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
Khaled N. Khasawneh
中科院分区：
文献类型：
--
作者：
Md. Shohidul Islam;Behnam Omidi;Khaled N. Khasawneh
基于机器学习的硬件恶意软件检测器 (HMD) 在防御系统抵御恶意软件方面具有潜在的改变游戏规则的优势。然而，头戴式显示器会遭受对抗性攻击；它们可以被有效地逆向工程并随后被规避，从而使恶意软件隐藏起来以逃避检测。对抗性逃避攻击需要在程序执行中添加良性功能才能逃避检测。针对这些攻击，在本文中，我们提出了 MonotonicHMD，这是使用单调特征构建的 HMD，以防御对抗性规避攻击。具体来说，MonotonicHMD 仅使用单调恶意功能构建。因此，Monotonic-HMD 确保对手无法通过简单地向恶意软件程序添加良性特征来逃避检测，因为它们未在 Monotonic-HMD 模型中使用。此外，添加恶意功能只会增加将输入程序检测为恶意软件的概率。我们的实验结果表明，单调头戴式显示器可以有效防御对抗性攻击，而不会牺牲显着的检测准确性，这可以解释为对恶意软件进行分类的安全成本。重要的是，我们的结果表明，对于可以完全逃避当前 HMD 的规避恶意软件，所提出的 Monotonic-HMD 实现了 83% 的检测准确度，并且即使在更激进的攻击下也能保持这种准确度。此外，Monotonic-HMD 将推理时间（即执行一次检测的时间）减少了 61.11%。此外，Monotonic-HMD 的硬件实现结果表明，与当前的 HMD 相比，Monotonic-HMD 可以节省面积和功耗。
Machine learning-based hardware malware detectors (HMDs) offer a potential game-changing advantage in defending systems against malware. However, HMDs suffer from adversarial attacks; they can be effectively reverse-engineered and subsequently be evaded, allowing malware to hide from detection. Adversarial evasion attacks requires adding benign features to the program execution to be able to evade detection. Against these attacks, in this paper, we propose MonotonicHMDs, which are HMDs built using monotonic features to defend against adversarial evasion attacks. Specifically, MonotonicHMDs are build using monotonic malicious features only. Thus, Monotonic-HMDs ensures that an adversary cannot evade the detection by simply adding benign features to the malware programs since they are not used in the Monotonic-HMD model. In addition, adding malicious features will only increase the probability of detecting the input program as malware. Our experimental results demonstrate that Monotonic-HMDs offer effective defense against adversarial attacks without sacrificing significant detection accuracy, which can be interpreted as a cost for security in classifying malware. Importantly, our results shows that for evasive malware that can completely evade current HMDs, the proposed Monotonic-HMDs achieve 83% detection accuracy and maintain this accuracy even under more aggressive attacks. Moreover, Monotonic-HMDs reduce the inference time, i.e., time to perform one detection, by 61.11%. Furthermore, the hardware implementation results of the Monotonic-HMDs shows that Monotonic-HMDs offers area and power consumption savings compared to current HMDs.