Poison Attack and Poison Detection on Deep Source Code Processing Models

Jia Li

doi:10.1145/3630008

2024-03-14

PRE

DOI：10.1145/3630008

原文求助

摘要

En 中文

In the software engineering (SE) community, deep learning (DL) has recently been applied to many source code processing tasks, achieving state-of-the-art results. Due to the poor interpretability of DL models, their security vulnerabilities require scrutiny. Recently, researchers have identified an emergent security threat to DL models, namely, poison attacks. The attackers aim to inject insidious backdoors into DL models by poisoning the training data with poison samples. The backdoors mean that poisoned models work normally with clean inputs but produce targeted erroneous results with inputs embedded with specific triggers. By using triggers to activate backdoors, attackers can manipulate poisoned models in security-related scenarios (e.g., defect detection) and lead to severe consequences. To verify the vulnerability of deep source code processing models to poison attacks, we present a poison attack approach for source code named CODEPOISONER as a strong imaginary enemy. CODEPOISONER can produce compilable and functionality-preserving poison samples and effectively attack deep source code processing models by poisoning the training data with poison samples. To defend against poison attacks, we further propose an effective poison detection approach named CODEDETECTOR. CODEDETECTOR can automatically identify poison samples in the training data. We apply CODEPOISONER and CODEDETECTOR to six deep source code processing models, including defect detection, clone detection, and code repair models. The results show that (1) CODEPOISONER conducts successful poison attacks with a high attack success rate (average: 98.3%, maximum: 100%). It validates that existing deep source code processing models have a strong vulnerability to poison attacks. (2) CODEDETECTOR effectively defends against multiple poison attack approaches by detecting (maximum: 100%) poison samples in the training data. We hope this work can help SE researchers and practitioners notice poison attacks and inspire the design of more advanced defense techniques.

Keyword:

Poison attack

poison detection

source code processing

deep learning