arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2004.07919cs.CRcs.LG
收藏

一种增强深度神经网络对抗恶意软件的框架

A Framework for Enhancing Deep Neural Networks Against Adversarial Malware

Nanjing University of Science and Technology(南京理工大学);Wuyi University(五邑大学);Case Western Reserve University(凯斯西储大学);University of Colorado Colorado Springs(科罗拉多大学科罗拉多斯普林斯分校);University of Texas at San Antonio(德克萨斯大学圣安东尼奥分校)

Deqiang Li, Qianmu Li, Yanfang Ye, Shouhuai Xu

摘要:

已知基于机器学习的恶意软件检测易受对抗性规避攻击的攻击。最先进的是,没有有效的防御这些攻击。作为对麻省理工学院林肯实验室组织的对抗性恶意软件分类挑战的回应,并与AAAI-19网络安全人工智能研讨会(AICS'2019)相关联,我们提出了六个指导原则来增强深度神经网络的鲁棒性。这些原则中的一些已经分散在文献中,但其他人在本文中首次介绍。在这六个原则的指导下,我们提出了一个防御框架,以增强深度神经网络对对抗性恶意软件规避攻击的鲁棒性。通过对Drebin Android恶意软件数据集进行实验,我们表明该框架可以达到98.49\%的准确率(平均)对抗灰箱攻击,攻击者知道一些关于防御的信息,防御者知道一些关于攻击的信息,准确率为89.14%。(平均而言)对抗更有能力的白盒攻击,其中攻击者知道关于防御的一切,而防御者知道关于攻击的一些信息。该框架通过实现76.02%的准确率赢得了AICS 2019年的挑战,其中攻击者(即,挑战组织者)知道框架或防御,我们(防御者)也不知道攻击。这一差距凸显了了解攻击的重要性。

英文摘要:

Machine learning-based malware detection is known to be vulnerable to adversarial evasion attacks. The state-of-the-art is that there are no effective defenses against these attacks. As a response to the adversarial malware classification challenge organized by the MIT Lincoln Lab and associated with the AAAI-19 Workshop on Artificial Intelligence for Cyber Security (AICS'2019), we propose six guiding principles to enhance the robustness of deep neural networks. Some of these principles have been scattered in the literature, but the others are introduced in this paper for the first time. Under the guidance of these six principles, we propose a defense framework to enhance the robustness of deep neural networks against adversarial malware evasion attacks. By conducting experiments with the Drebin Android malware dataset, we show that the framework can achieve a 98.49\% accuracy (on average) against grey-box attacks, where the attacker knows some information about the defense and the defender knows some information about the attack, and an 89.14% accuracy (on average) against the more capable white-box attacks, where the attacker knows everything about the defense and the defender knows some information about the attack. The framework wins the AICS'2019 challenge by achieving a 76.02% accuracy, where neither the attacker (i.e., the challenge organizer) knows the framework or defense nor we (the defender) know the attacks. This gap highlights the importance of knowing about the attack.

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。

↑