An empirical evaluation of mainstream Rust SAST tools using security vulnerabilities identified in real-world Rust applications is conducted and a large language model (LLM)-assisted automated testing framework, TRUST, is proposed, which automatically analyzes the official Rust reference to derive and implement semanti...
Huai-En Zhang, Zheng-Jie Zhao, Yu Pei et al.· 0 citations
LLM4SAST is presented, the first universal framework detecting faults in SAST tools using large language models and dynamic feedback, and its key insight is leveraging LLMs to understand and transform code in diverse programming languages.
Huai-En Zhang, Yu Pei, Hao Chen et al.· 0 citations
The first systematic security study of NES systems is conducted, finding that NES retrieves a significantly expanded context, including inputs from imperceptible user actions and global codebase retrieval, which increases the attack surfaces.