Anqi Zhang's Homepage

I am a Ph.D. student of Computer Science at New York University (NYU, Courant) advised by Prof. Jinyang Li and Prof. Aurojit Panda.

My research interests are in Machine Learning Security and Trustworthy AI, in particular, explanability of the black-box models, adversarial attacks, defenses and poison detection. Recently, I’m interested in the explanation and transpacency problems in large language models.

Prior to strating at NYU, I was a pre-doctoral master student at University of Chicago(UChicago), advised by Prof. Haryadi S. Gunawi, researched on applying deep learning models for storage system. Before that, I got my B.S. degree from Beijing University of Posts and Telecommunications(BUPT).

Click here for my CV. Contact me: Anqi.Zhang at nyu.edu