Principal Researcher, Microsoft Research, India
How to Train and Use AI Models on Sensitive Data without Compromising Privacy?
Abstract: AI models have the potential to revolutionize many domains, but they also pose serious privacy risks. How can we ensure that our data is not exposed or misused when we train or use these models? How can we protect the intellectual property of the model publishers and the privacy of the data owners?
In this talk, I will introduce EzPC, a system developed by Microsoft Research that enables privacy preserving machine learning. I will show how EzPC leverages cryptographic techniques to allow secure and efficient computation on encrypted data, without revealing any information to any party. I will also present some of the recent advances and challenges in this exciting area of research.
Nishanth Chandran is a Principal Researcher at Microsoft Research, India. His research interests are in problems related to cryptography, cloud security, confidential computing and secure computation. Prior to joining MSRI, Nishanth was a Researcher at AT&T Labs, and before that he was a Post-doctoral Researcher at MSR Redmond.
Nishanth is a recipient of the 2010 Chorafas Award for exceptional achievements in research and his research has received coverage in science journals and in the media at venues such as Nature and MIT Technology Review. He has published several papers in top computer science conferences and journals such as Crypto, Eurocrypt, IEEE S&P, CCS, STOC, FOCS, SIAM Journal of Computing, Journal of the ACM, and so on. His work on position-based cryptography was selected as one of the top 3 works and invited to QIP 2011 as a plenary talk.