0

CodeAttack: Code-Based Adversarial Attacks for Pre-trained Programming Language Models

CodeAttack is a black-box adversarial attack model targeting pre-trained programming language models through code structure, demonstrating vulnerabilities and outperforming state-of-the-art adversarial models in various tasks.

Year
2022
Venue
arXiv 2022
Authors
2
Hosting
Abstract onlyARXIV-DEFAULT

Cite

Notes

Only stored in your browser.

Attribution

Abstract & full text
arxiv.org/abs/2206.00052v3ARXIV-DEFAULT
TL;DR
Semantic Scholar
Attribution policy →

Abstract

Pre-trained programming language (PL) models (such as CodeT5, CodeBERT, GraphCodeBERT, etc.,) have the potential to automate software engineering tasks involving code understanding and code generation. However, these models operate in the natural channel of code, i.e., they are primarily concerned with the human understanding of the code. They are not robust to changes in the input and thus, are potentially susceptible to adversarial attacks in the natural channel. We propose, CodeAttack, a simple yet effective black-box attack model that uses code structure to generate effective, efficient, and imperceptible adversarial code samples and demonstrates the vulnerabilities of the state-of-the-art PL models to code-specific adversarial attacks. We evaluate the transferability of CodeAttack on several code-code (translation and repair) and code-NL (summarization) tasks across different programming languages. CodeAttack outperforms state-of-the-art adversarial NLP attack models to achieve the best overall drop in performance while being more efficient, imperceptible, consistent, and fluent. The code can be found at https://github.com/reddy-lab-code-research/CodeAttack.

Authors

2