Pengrun Huang (黄鹏润)

I am Pengrun Huang, a third-year Ph.D. student in the Computer Science and Engineering Department at the University of California, San Diego. I am fortunate to be co-advised by Kamalika Chaudhuri and Yu-Xiang Wang. Previously, I earned my bachelor’s and master’s degrees in Honors Mathematics from University of Michigan. I was mentored by Maggie Makar.

I work on trustworthy ML, data privacy and confidentiality, with a current emphasis on large language models (LLMs). In particular, I am interested in:

• Identifying training data privacy and confidentiality risk.
• Measuring model memorization.
• Designing defense strategy for privacy attacks.

Selected Publications