arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.06747cs.CRcs.AI
收藏

恶意软件的可实现的通用对抗性扰动

Realizable Universal Adversarial Perturbations for Malware

Universität der Bundeswehr München(慕尼黑联邦国防军大学);Imperial College London(帝国理工学院);University College London(伦敦大学学院);King’s College London(伦敦国王学院)

Raphael Labaca-Castro, Luis Muñoz-González, Feargus Pendlebury, Gabi Dreo Rodosek, Fabio Pierazzi, Lorenzo Cavallaro

摘要:

机器学习分类器容易受到对抗性示例的影响--特定于输入的扰动会操纵模型的输出。通用对抗性扰动(Universal Adversarial Perturbations,UAPs)识别在输入空间中泛化的噪声模式,允许攻击者极大地扩展此类示例的生成。虽然UAP已经在计算机视觉以外的应用领域进行了探索,但在可实现的攻击(例如恶意软件)的特定上下文中,对其属性和影响知之甚少,其中攻击者必须满足具有挑战性的问题空间约束。在本文中,我们将探讨在恶意软件分类的背景下,UAP的挑战和优势。我们生成的序列的问题空间的转换,诱导UAP在相应的特征空间嵌入和评估其有效性在不同的恶意软件域。此外,我们提出了基于对抗训练的缓解措施,使用从问题空间转换中获得的知识,并与其他特征空间防御进行比较。我们的实验将白盒Android规避攻击的有效性限制在约20%,成本为约3% TPR和1% FPR。我们还展示了我们的方法如何适用于更严格的域,如Windows恶意软件。我们观察到,虽然特征空间中的对抗性训练必须处理大型且通常不受约束的区域,但问题空间中的UAP识别特定的漏洞,使我们能够更有效地强化分类器,将识别新的通用对抗性转换的挑战和相关成本转移回攻击者。

英文摘要:

Machine learning classifiers are vulnerable to adversarial examples -- input-specific perturbations that manipulate models' output. Universal Adversarial Perturbations (UAPs), which identify noisy patterns that generalize across the input space, allow the attacker to greatly scale up the generation of such examples. Although UAPs have been explored in application domains beyond computer vision, little is known about their properties and implications in the specific context of realizable attacks, such as malware, where attackers must satisfy challenging problem-space constraints. In this paper we explore the challenges and strengths of UAPs in the context of malware classification. We generate sequences of problem-space transformations that induce UAPs in the corresponding feature-space embedding and evaluate their effectiveness across different malware domains. Additionally, we propose adversarial training-based mitigations using knowledge derived from the problem-space transformations, and compare against alternative feature-space defenses. Our experiments limit the effectiveness of a white box Android evasion attack to ~20% at the cost of ~3% TPR at 1% FPR. We additionally show how our method can be adapted to more restrictive domains such as Windows malware. We observe that while adversarial training in the feature space must deal with large and often unconstrained regions, UAPs in the problem space identify specific vulnerabilities that allow us to harden a classifier more effectively, shifting the challenges and associated cost of identifying new universal adversarial transformations back to the attacker.

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。

↑