About Me

I am a senior undergraduate student at Tsinghua University majoring in Electronic Engineering. I am interested in developing robust defense mechanisms against emerging AI security threats, particularly in Large Language Model (LLM) security.

Currently, I work as a research assistant at UC Berkeley, collaborating with Sizhe Chen under the guidance of Prof. David Wagner. My current project involves building deployable defenses against prompt injection attacks targeting LLMs, focusing on creating practical security solutions for real-world AI systems.

I had an impactful six-month research experience at the University of Illinois Urbana-Champaign (UIUC), where I worked on developing anti-phishing LLM agents and exploring human factors in phishing attacks under the supervision of Prof. Gang Wang. This work resulted in a publication at SOUPS 2025. Prior to this, I conducted research about intelligent city with Prof. Yong Li at Tsinghua University.

I aim to contribute to the development of safer and more trustworthy AI systems for real-world deployment, bridging the gap between theoretical security research and practical applications in cybersecurity.