arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2108.00669cs.CRcs.LG
收藏

使基于深度学习的漏洞检测器健壮

Towards Making Deep Learning-based Vulnerability Detectors Robust

Huazhong University of Science and Technology(华中科技大学);University of Texas at San Antonio(德克萨斯大学圣安东尼奥分校);University of Colorado Colorado Springs(科罗拉多大学科罗拉多斯普林斯分校);Tsinghua University(清华大学)

Zhen Li, Jing Tang, Deqing Zou, Qian Chen, Shouhuai Xu, Chao Zhang, Yichen Li, Hai Jin

摘要:

自动检测源代码中的软件漏洞是一个备受关注的重要问题。特别是,基于深度学习的漏洞检测器或基于DL的检测器是有吸引力的,因为它们不需要人类专家来定义漏洞的特征或模式。然而,这种检测器的鲁棒性尚不清楚。在本文中,我们开始在这方面的研究表明,基于DL的检测器是不强大的简单的代码转换,在本文中被称为攻击,因为这些转换可能会被用于恶意目的。作为使基于DL的检测器对此类攻击具有鲁棒性的第一步,我们提出了一个创新的框架,称为ZigZag,其中心是(i)解耦特征学习和分类器学习,以及(ii)使用ZigZag风格的策略迭代地改进它们,直到它们收敛到鲁棒的特征和鲁棒的分类器。实验结果表明,ZigZag框架可以大大提高基于DL的检测器的鲁棒性。

英文摘要:

Automatically detecting software vulnerabilities in source code is an important problem that has attracted much attention. In particular, deep learning-based vulnerability detectors, or DL-based detectors, are attractive because they do not need human experts to define features or patterns of vulnerabilities. However, such detectors' robustness is unclear. In this paper, we initiate the study in this aspect by demonstrating that DL-based detectors are not robust against simple code transformations, dubbed attacks in this paper, as these transformations may be leveraged for malicious purposes. As a first step towards making DL-based detectors robust against such attacks, we propose an innovative framework, dubbed ZigZag, which is centered at (i) decoupling feature learning and classifier learning and (ii) using a ZigZag-style strategy to iteratively refine them until they converge to robust features and robust classifiers. Experimental results show that the ZigZag framework can substantially improve the robustness of DL-based detectors.

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。

↑