Machine Learning on Encrypted Data: Hardware to the Rescue

Abstract

Machine Learning on encrypted data is a yet-to-be-addressed challenge. Several recent key advances across different layers of the system, from cryptography and mathematics to logic synthesis and hardware are paving the way for practical realization of privacy preserving computing for certain target applications. This talk highlights the crucial role of hardware and advances in computing architecture in supporting the recent progresses in the field. I outline the main technologies and mixed computing models. I particularly center my talk on the recent progress in synthesis of Garbled Circuits that provide a leap in scalable realization of machine learning on encrypted data. I explore how hardware could pave the way for navigating the complex space of privacy-preserving computing in general, and enabling scalable future mixed protocol solutions. I conclude by briefly discussing the challenges and opportunities moving forward.