I am a second-year Ph.D. student at Michigan State University, co-advised by Prof. Jiliang Tang and Prof. Hui Liu. Prior to this, I received my bachelor’s degree from University of Science and Technology of China (USTC), School of Mathematics. My research interests lie in AI Agents and Trustworthy AI, and I am devoted to developing intelligent agent systems that are both capable and reliable.

If you would like to explore potential collaborations or are interested in related research, feel free to get in touch 😊！

📝 Publications

• A Practical Memory Injection Attack Against LLM Agents
  *S Dong, *S Xu, P He, Y Li, J Tang, T Liu, H Liu, Z Xiang; Preprint 2025

• Comprehensive Vulnerability Analysis is Necessary for Trustworthy LLM-MAS
  P He, Y Xing, S Dong, J Li, Z Dai, X Tang, H Liu, H Xu, Z Xiang, …; Preprint 2025

• Red-teaming LLM Multi-Agent Systems via Communication Attacks
  P He, Y Lin, S Dong, H Xu, Y Xing, H Liu; ACL Findings 2025

📖 Educations

• 2024.08 - (now), Michigan State University, CSE, Ph.D.
• 2020.09 - 2024.06, University of Science and Technology of China, Mathematics, Bachelor.