Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Yuepeng Hu

Yuepeng Hu

2 indexed papers

Recent (6 mo)
2
With code
0
Influential cites
0
Benchmarked
0

Publications per year

2
26

Top categories

Crypto×2Software Eng.×1Vision×1AI×1ML×1

Frequent co-authors

Taein Kim1×
David Jiang1×
Yuqi Jia1×
Neil Gong1×
Zedian Shao1×
Hongbin Liu1×

Research Timeline

2026
Leave My Images Alone: Preventing Multi-Modal Large Language Models from Analyzing Images via Visual Prompt Injection

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.

Evaluating Tool Cloning in Agentic-AI Ecosystems

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.

Highlighted terms show continued research focus across papers

Papers

cs.SEcs.CRRecentMay 10, 2026

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…

View →
cs.CVcs.AIcs.CRRecentApr 10, 2026

Leave My Images Alone: Preventing Multi-Modal Large Language Models from Analyzing Images via Visual Prompt Injection

Zedian Shao, Hongbin Liu, Yuepeng Hu, Neil Zhenqiang Gong

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 sensiti…

View →