collaborators

13 papers

cs.CR2026

Dynamic Malicious Skills in Agentic AI

Tianhao Chen, Zhengyuan Jiang, Yuepeng Hu +2

Skills are a key enabling component of agentic AI. While they enhance agents' capabilities, they also introduce new attack surfaces. In this work, we investigate one such attack su…

cs.CR2026

Fingerprinting LLMs via Prompt Injection

Yuepeng Hu, Zhengyuan Jiang, Mengyuan Li +4

Large language models (LLMs) are often modified after release through post-processing such as post-training or quantization, which makes it challenging to determine whether one mod…

cs.SE2026

Evaluating Tool Cloning in Agentic-AI Ecosystems

Taein Kim, David Jiang, Yuepeng Hu +2

Agent tools are becoming a core interface through which LLM agents access external data, services, and execution environments. As these tools are distributed through public marketp…

cs.CR2026

MalTool: Malicious Tool Attacks on LLM Agents

Yuepeng Hu, Yuqi Jia, Mengyuan Li +2

In a malicious tool attack, an attacker uploads a malicious tool to a distribution platform; once a user inadvertently installs the tool and the LLM agent selects it during task ex…

cs.CV2026

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

Zedian Shao, Hongbin Liu, Yuepeng Hu +1

Multi-modal large language models (MLLMs) have emerged as powerful tools for analyzing Internet-scale image data, offering significant benefits but also raising critical safety and…

cs.CR2026

Watermark-based Attribution of AI-Generated Content

Zhengyuan Jiang, Moyang Guo, Yuepeng Hu +2

Several companies have deployed watermark-based detection to identify AI-generated content. However, attribution--the ability to trace back to the user of a generative AI (GenAI) s…