English

CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion

Computation and Language 2024-09-17 v5 Artificial Intelligence Cryptography and Security Machine Learning Software Engineering

Abstract

The rapid advancement of Large Language Models (LLMs) has brought about remarkable generative capabilities but also raised concerns about their potential misuse. While strategies like supervised fine-tuning and reinforcement learning from human feedback have enhanced their safety, these methods primarily focus on natural languages, which may not generalize to other domains. This paper introduces CodeAttack, a framework that transforms natural language inputs into code inputs, presenting a novel environment for testing the safety generalization of LLMs. Our comprehensive studies on state-of-the-art LLMs including GPT-4, Claude-2, and Llama-2 series reveal a new and universal safety vulnerability of these models against code input: CodeAttack bypasses the safety guardrails of all models more than 80\% of the time. We find that a larger distribution gap between CodeAttack and natural language leads to weaker safety generalization, such as encoding natural language input with data structures. Furthermore, we give our hypotheses about the success of CodeAttack: the misaligned bias acquired by LLMs during code training, prioritizing code completion over avoiding the potential safety risk. Finally, we analyze potential mitigation measures. These findings highlight new safety risks in the code domain and the need for more robust safety alignment algorithms to match the code capabilities of LLMs.

Keywords

Cite

@article{arxiv.2403.07865,
  title  = {CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion},
  author = {Qibing Ren and Chang Gao and Jing Shao and Junchi Yan and Xin Tan and Wai Lam and Lizhuang Ma},
  journal= {arXiv preprint arXiv:2403.07865},
  year   = {2024}
}

Comments

ACL Findings 2024, Code is available at https://github.com/renqibing/CodeAttack

R2 v1 2026-06-28T15:17:38.218Z