Towards Making Deep Learning-based Vulnerability Detectors Robust

Abstract

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.

References in corpus (7)

• $\mu$VulDeePecker: A Deep Learning-Based System for Multiclass Vulnerability Detection
• Imperceptible, Robust, and Targeted Adversarial Examples for Automatic Speech Recognition
• Devign: Effective Vulnerability Identification by Learning Comprehensive Program Semantics via Graph Neural Networks
• Learning to Repair Software Vulnerabilities with Generative Adversarial Networks
• Defense Against the Dark Arts: An overview of adversarial example security research and future research directions
• COSET: A Benchmark for Evaluating Neural Program Embeddings
• Testing Neural Program Analyzers

Cited by in corpus (1)

• An Unbiased Transformer Source Code Learning with Semantic Vulnerability Graph