Huaijin Wang
2 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
The paper introduces ReproMIA, a novel and efficient framework that uses model reprogramming to proactively amplify and detect latent privacy leakage for Membership Inference Attacks (MIAs), significantly outperforming state-of-the-art methods, especially in low False Positive Rate regimes.
SkillScope introduces a graph-based framework to enforce fine-grained least-privilege in LLM Agent Skills, significantly reducing over-privileged actions while maintaining task functionality.
Papers
SkillScope: Toward Fine-Grained Least-Privilege Enforcement for Agent Skills
Jiangrong Wu, Yuhong Nan, Yixi Lin, Huaijin Wang +3 more
SkillScope introduces a graph-based framework to enforce fine-grained least-privilege in LLM Agent Skills, significantly reducing over-privileged actions while maintaining task functionality.