I am a first-year PhD student in Computer Science at Johns Hopkins University, advised by Prof. Yinzhi Cao, Prof. Yaxing Yao, and Prof. Ziyang Li. Before joining JHU, I received my bachelor's degree in Software Engineering at Xi'an Jiaotong University advised by Prof. Wei Ke

My research develops secure and human-centered AI systems, focusing on the safety, privacy, and robustness of multimodal and agentic models in real-world environments. I am particularly interested in understanding how large language and vision-language models behave when they interact with users, external tools, and safety-critical physical systems. My work studies both the vulnerabilities of these systems, and their potential to support users. I aim to build AI systems that are trustworthy not only in model performance, but also in security, usability, and alignment with human goals.