Executive Briefing: Advances in privacy for machine learning systems

Katharine Jarmul sates your curiosity about how far we’ve come in implementing privacy within machine learning systems. She dives into recent advances in privacy measurements and explains how this changed the approach of privacy in machine learning. You’ll discover new techniques including differentially private data collection, federated learning, and homomorphic techniques.

She also explores why privacy has become more important since the advent of machine learning and the push that companies like Apple have put on retaining privacy for end users. You’ll approach the questions of why privacy is important now, if it’ll become more important, how this will affect the machine learning community as a whole, and other deeper questions interlaced with technical and theoretical discussion.