Lingzhi Yuan

I’m currently a final year Undergraduate Student majoring in Automation at Zhejiang University (ZJU). I am also a research internship student at University of Chicago (UChi), Secure Learning Lab advised by Professor Bo Li. Before that, I was also a research student at USSLAB advised by Professor Yanjiao Chen and Professor Xiaoyu Ji.

Besides that, I am also a member of Intensive Training Honors Program of Innovation and Entrepreneurship (ITP) at Chu Kochen Honors College.

My current research primarily concentrates on Trustworthy Machine Learning, with a particular emphasis on enhancing the safety and robustness of advanced models. My research centers on exploring the vulnerability of cutting-edge ML models, especially Multi-modal Models (Text-to-Image model, VLM, Audio LLM etc.) and developing reliable defense mechanisms to safeguard their widespread deployments. By tackling these challenges, I aim to contribute to the development of AI technologies that are not only high-performing but also secure, transparent, and aligned with ethical standards.

You could refer to my resume for more detail.

Find other interesting things about me in this page🧩!