一作ACL 2026Poster· Natural Language Processing
R ed C oder: Automated Multi-Turn Red Teaming for Code LLM s
Wenjie Jacky Mo · Qin Liu · Xiaofei Wen · Dongwon Jung · Hadi Askari · Wenxuan Zhou · Zhe Zhao · Muhao Chen
摘要
Large Language Models (LLMs) for code generation (i.e., Code LLMs) have demonstrated impressive capabilities in AI-assisted software development and testing. However, recent studies have shown that these models are prone to generating vulnerable or even malicious code under adversarial settings....