5 papers
Learn from Your Mistakes: Tree-like Self-Play for Secure Code LLMs
Wenqi Chen, Ziyan Zhang, Bin Wang +3
While Large Language Models (LLMs) excel in code generation, they remain prone to replicating subtle yet critical vulnerabilities endemic to their training data. Current alignment…
Is Your Prompt Poisoning Code? Defect Induction Rates and Security Mitigation Strategies
Bin Wang, YiLu Zhong, MiDi Wan +4
Large language models (LLMs) have become indispensable for automated code generation, yet the quality and security of their outputs remain a critical concern. Existing studies pred…
Learning to Generate Secure Code via Token-Level Rewards
Jiazheng Quan, Xiaodong Li, Bin Wang +5
Large language models (LLMs) have demonstrated strong capabilities in code generation, yet they remain prone to producing security vulnerabilities. Existing approaches commonly suf…
AI Code in the Wild: Measuring Security Risks and Ecosystem Shifts of AI-Generated Code in Modern Software
Bin Wang, Wenjie Yu, Yilu Zhong +6
Large language models (LLMs) for code generation are becoming integral to modern software development, but their real-world prevalence and security impact remain poorly understood.…
A.S.E: A Repository-Level Benchmark for Evaluating Security in AI-Generated Code
Keke Lian, Bin Wang, Lei Zhang +19
The increasing adoption of large language models (LLMs) in software engineering necessitates rigorous security evaluation of their generated code. However, existing benchmarks ofte…