2 papers
cs.SE2024
CKGFuzzer: LLM-Based Fuzz Driver Generation Enhanced By Code Knowledge Graph
Hanxiang Xu, Wei Ma, Ting Zhou +5
In recent years, the programming capabilities of large language models (LLMs) have garnered significant attention. Fuzz testing, a highly effective technique, plays a key role in e…
cs.CR2024
PathSeeker: Exploring LLM Security Vulnerabilities with a Reinforcement Learning-Based Jailbreak Approach
Zhihao Lin, Wei Ma, Mingyi Zhou +5
In recent years, Large Language Models (LLMs) have gained widespread use, raising concerns about their security. Traditional jailbreak attacks, which often rely on the model intern…