Published multiple papers in top conferences such as USENIX Security Symposium, IEEE Symposium on Security and Privacy, ICLR. Some notable papers include: 'PoisonedRAG: Knowledge Poisoning Attacks to Retrieval-Augmented Generation of Large Language Models', 'Formalizing and Benchmarking Prompt Injection Attacks and Defenses', 'FCert: Provably Robust Few-Shot Classification in the Era of Foundation Model'.
Research Experience
Postdoc at the University of Illinois Urbana-Champaign, supervised by Prof. Bo Li.
Education
Ph.D. from Duke University's Department of Electrical and Computer Engineering in 2022, under the supervision of Prof. Neil Zhenqiang Gong; M.E. from Iowa State University in 2019; B.E. from the University of Science and Technology of China (USTC) in 2016.
Background
Currently an Assistant Professor of Information Sciences and Technology at Pennsylvania State University. Research interests include: 1) identifying security/safety issues (e.g., poisoning attacks, prompt injection, and jailbreak) of LLM-empowered AI systems, and 2) enhancing the trustworthiness (e.g., transparency) of these systems.
Miscellany
Currently advising several Ph.D. students, including Chenlong Yin, Runpeng Geng, Yanting Wang, and Wei Zou.