Homomorphic encryption (HE) is an encryption method to enable arbitrary computation on encrypted data without decrypting them. It has emerged as one of the promising solutions to address privacy issues in computation over sensitive data. In this talk, I will introduce the recent technical advance of HE-based privacy-preserving machine learning including the state-of-the-art benchmark results.

Miran Kim is an assistant professor of the Department of Mathematics and affiliated with the Department of Computer Science at Hanyang University. Miran Kim received her Ph.D. in mathematical sciences at Seoul National University, Korea, in 2017. Her research focuses on the design of novel strategies to enable secure and privacy-preserving data analysis using homomorphic encryption. She has extensive experience in the implementation of efficient protocols for data query processing, genome analysis, and machine learning.