Yuepeng Hu
2 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
The paper introduces ImageProtector, a user-side method that embeds an imperceptible perturbation into images to prevent Multi-modal Large Language Models (MLLMs) from analyzing and extracting sensitive information from them.
The paper presents a large-scale study demonstrating that tool cloning is a pervasive and severe source of hidden duplication in agent-tool ecosystems, necessitating changes in how tool diversity is measured.
Papers
Evaluating Tool Cloning in Agentic-AI Ecosystems
Taein Kim, David Jiang, Yuepeng Hu, Yuqi Jia +1 more
The paper presents a large-scale study demonstrating that tool cloning is a pervasive and severe source of hidden duplication in agent-tool ecosystems, necessitating changes in how tool diversity is m…