报告题目：MachineLearning with Privacy—Cryptographic Approach and SGX+GPU Approach
报告人：Sherman S.M. Chow
报告内容：The combination of cloud-based computing paradigm and machine learning algorithms has enabled many complex analytic services, such as face recognition in a crowd or valuation of immovable properties. Companies can charge clients who do not have the expertise or resource to build such complex models for the prediction or classification service. Many useful applications of machine learning involve sensitive data. Yet, cryptographic solutions for privacy-preserving machine learning are still not that satisfactory. In this presentation, we discuss how to enable privacy-preserving machine learning based on additive homomorphic encryption instead of somewhat/fully homomorphic encryption, and based on trusted Processors and graphicsprocessing units.
报告人简介：Sherman S.M. Chow joinedChinese University Of Hong Kong (CUHK) in November 2012 and received the Early Career Award from Hong Kong RGC. He got his PhD from New York University and did his post-doc in University of Waterloo. He is an assistant professor of the Department of Information Engineering atCUHK.
His main interests are in Cryptography,Security, and Privacy, with publicationsin CCS,Eurocrypt, ITCS, NDSS, USENIX Security, Asiacrypt, AsiaCCS and so on. He served on the program committee of Asiacrypt for 6 years and other top-tier conferences like CRYPTO and TheWeb in 2019. He is a distinguished TPC of Infocom 2018, and co-chaired CANS, ISC, and ProvSec before. He is also on the editorial boards of a number of journals including “IEEE Transactions on Information Forensics and Security (TIFS)” and a book series by Springer on “Cyber Security Systems and Networks”.