5 papers
Do Skill Descriptions Tell the Truth? Detecting Undisclosed Security Behaviors in Code-Backed LLM Skills
Wenhui He, Yue Li, Bang Fu +4
Programmatic skills in LLM ecosystems consist of a natural-language description and executable implementation files. Users and LLMs rely on the description to understand the skill'…
Usability as a Weapon: Attacking the Safety of LLM-Based Code Generation via Usability Requirements
Yue Li, Xiao Li, Hao Wu +5
Large Language Models (LLMs) are increasingly used for automated software development, making their ability to preserve secure coding practices critical. In practice, however, many…
A Systematic Study of Code Obfuscation Against LLM-based Vulnerability Detection
Xiao Li, Yue Li, Hao Wu +4
As large language models (LLMs) are increasingly adopted for code vulnerability detection, their reliability and robustness across diverse vulnerability types have become a pressin…
When LLMs Copy to Think: Uncovering Copy-Guided Attacks in Reasoning LLMs
Yue Li, Xiao Li, Hao Wu +4
Large Language Models (LLMs) have become integral to automated code analysis, enabling tasks such as vulnerability detection and code comprehension. However, their integration intr…
Everything You Wanted to Know About LLM-based Vulnerability Detection But Were Afraid to Ask
Yue Li, Xiao Li, Hao Wu +5
Large Language Models are a promising tool for automated vulnerability detection, thanks to their success in code generation and repair. However, despite widespread adoption, a cri…