13 papers
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…
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…
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…
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…
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…
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…