Rényi Differential Privacy — Ilya Mironov

Abstract: We discuss a natural relaxation of differential privacy based on the Renyi divergence. Closely related notions have appeared in several recent papers that analyzed composition of differentially private mechanisms. We argue that the useful analytical tool can be used as a privacy definition, compactly and accurately representing guarantees on the tails of the privacy loss distribution, and discuss its recent applications in privacy-preserving machine learning.

Bio: Ilya Mironov is a Staff Research Scientist in Google Brain working on security and privacy of machine learning. Prior to joining Google, he was a member of Microsoft Research Silicon Valley (2003-2014). He holds a Ph.D. in Computer Science from Stanford.