5 papers
Metis: Learning to Jailbreak LLMs via Self-Evolving Metacognitive Policy Optimization
Huilin Zhou, Jian Zhao, Yilu Zhong +7
Red teaming is critical for uncovering vulnerabilities in Large Language Models (LLMs). While automated methods have improved scalability, existing approaches often rely on static…
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…
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.…
RefleXGen:The unexamined code is not worth using
Bin Wang, Hui Li, AoFan Liu +7
Security in code generation remains a pivotal challenge when applying large language models (LLMs). This paper introduces RefleXGen, an innovative method that significantly enhance…
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…