Kristin Lauter is director of West Coast AI Research, Meta. Fellow of the American Association for the Advancement of Science, Fellow of the American Mathematical Society, Honorary Member of the Royal Mathematical Society of Spain, Fellow of the Society of Industrial and Applied Mathematics, Fellow and Past President of the Association for Women in Mathematics, Affiliate Professor University of Washington.
Abstract – Private AI for human health and genomic data
Artificial Intelligence shows tremendous promise for improving human health, but the privacy risks inherent in collecting and handling human health data are many. Private AI is based on Homomorphic Encryption (HE), a new encryption paradigm which allows the cloud to operate on private data in encrypted form, without ever decrypting it, enabling private training and private prediction on health data. In 2016 the ICML CryptoNets paper showed for the first time that it was possible to evaluate neural nets on homomorphically encrypted data, and opened new research directions combining machine learning and cryptography. The security of Homomorphic Encryption is based on hard problems in mathematics involving lattices, a candidate for post-quantum cryptography. This talk will explain Homomorphic Encryption, Private AI, and show HE in action for protecting health and genomic data.