I am a senior undergraduate student at Tsinghua University majoring in Electronic Engineering. My research focuses on AI security, particularly developing robust defenses against emerging threats to AI systems. I am broadly interested in safety and security topics, including hallucination, interpretability, copyright protection, and reliable reasoning.

During Summer 2025, I worked at UC Berkeley with Prof. David Wagner and PhD student Sizhe Chen on defenses against prompt injection attacks. This work led to publications at SaTML 2026 and AISec@CCS 2025.

Prior to that, I was fortunate to work at UIUC with Prof. Gang Wang on leveraging LLM-based agents for explainable phishing detection, leading to a publication at SOUPS 2025.

I am applying to PhD programs for Fall 2026. Feel free to reach out via email for collaboration or opportunities!