arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2203.12980cs.CRcs.AI
收藏

MERLIN --利用强化学习规避恶意软件

MERLIN -- Malware Evasion with Reinforcement LearnINg

Orange Innovation(Orange创新研究院);University of Caen Normandy(卡昂诺曼底大学)

Tony Quertier, Benjamin Marais, Stéphane Morucci, Bertrand Fournel

摘要:

除了基于签名和基于统计学的检测技术之外,机器学习(ML)还被广泛用于推广新的、从未见过的恶意软件(恶意软件)。然而,已经证明,ML模型可以通过欺骗分类器返回错误的标签来欺骗。例如,这些研究通常依赖于对基于梯度的攻击很脆弱的预测分数。在攻击者几乎没有关于恶意软件检测引擎的输出的信息的更现实的情况下,实现了适度的规避率。在本文中,我们提出了一种使用强化学习与DQN和REINFORCE算法的方法,以挑战两个最先进的基于ML的检测引擎(MalConv \& EMBER)和Gartner分类为领导者AV的商业AV。我们的方法结合了几个动作,修改Windows可移植执行(PE)文件,而不会破坏其功能。我们的方法还可以识别哪些操作执行得更好,并编译详细的漏洞报告,以帮助减轻规避。我们证明,REINFORCE实现了非常好的逃避率,即使在商业AV有限的可用信息。

英文摘要:

In addition to signature-based and heuristics-based detection techniques, machine learning (ML) is widely used to generalize to new, never-before-seen malicious software (malware). However, it has been demonstrated that ML models can be fooled by tricking the classifier into returning the incorrect label. These studies, for instance, usually rely on a prediction score that is fragile to gradient-based attacks. In the context of a more realistic situation where an attacker has very little information about the outputs of a malware detection engine, modest evasion rates are achieved. In this paper, we propose a method using reinforcement learning with DQN and REINFORCE algorithms to challenge two state-of-the-art ML-based detection engines (MalConv \& EMBER) and a commercial AV classified by Gartner as a leader AV. Our method combines several actions, modifying a Windows portable execution (PE) file without breaking its functionalities. Our method also identifies which actions perform better and compiles a detailed vulnerability report to help mitigate the evasion. We demonstrate that REINFORCE achieves very good evasion rates even on a commercial AV with limited available information.

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。

↑