StratDef：针对基于机器学习的恶意软件检测中对抗性攻击的战略防御
StratDef: Strategic Defense Against Adversarial Attacks in ML-based Malware Detection
AI总结：
提出基于移动目标防御的 StratDef 系统，通过动态策略化选择模型降低攻击可迁移性，并在多威胁级别下证明其优于现有恶意软件检测防御。
摘要：
多年来，大多数针对机器学习模型对抗性攻击防御的研究都集中在图像识别领域。尽管基于机器学习的恶意软件检测领域十分重要，但其受到的关注较少。此外，大多数探索这些防御的工作都集中在若干方法上，但在应用这些方法时缺乏策略。在本文中，我们提出了 StratDef，这是一个基于移动目标防御方法的战略防御系统。我们克服了与模型的系统化构建、选择和战略性使用相关的挑战，以最大化对抗鲁棒性。StratDef 动态且策略性地选择最佳模型，以增加攻击者的不确定性，同时最小化对抗机器学习领域中的关键方面，例如攻击可迁移性。我们首次全面评估了针对恶意软件检测中机器学习对抗性攻击的防御，其中我们的威胁模型探索了不同级别的威胁、攻击者知识、能力和攻击强度。我们表明，即使面对最强的对抗性威胁，StratDef 的表现也优于其他防御。我们还表明，在现有防御中，只有少数对抗训练模型比仅使用普通模型提供显著更好的保护，但其表现仍不及 StratDef。
英文摘要：
Over the years, most research towards defenses against adversarial attacks on machine learning models has been in the image recognition domain. The ML-based malware detection domain has received less attention despite its importance. Moreover, most work exploring these defenses has focused on several methods but with no strategy when applying them. In this paper, we introduce StratDef, which is a strategic defense system based on a moving target defense approach. We overcome challenges related to the systematic construction, selection, and strategic use of models to maximize adversarial robustness. StratDef dynamically and strategically chooses the best models to increase the uncertainty for the attacker while minimizing critical aspects in the adversarial ML domain, like attack transferability. We provide the first comprehensive evaluation of defenses against adversarial attacks on machine learning for malware detection, where our threat model explores different levels of threat, attacker knowledge, capabilities, and attack intensities. We show that StratDef performs better than other defenses even when facing the peak adversarial threat. We also show that, of the existing defenses, only a few adversarially-trained models provide substantially better protection than just using vanilla models but are still outperformed by StratDef.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
