Abstract: As the world adopts Artificial Intelligence, the privacy risks are many. AI can improve our lives, but may leak our private data. 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. Our 2016 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 explain HE in action.
Speaker Bio: Dr. Kristin Lauter is West Coast Director of Research Science for Meta: Facebook AI Research (FAIR), leading the Seattle and Menlo Park Labs with groups in Core Machine Learning, Computer Vision, Robotics, Natural Language Processing, and other areas. Her research focuses on Private AI, homomorphic encryption, and post-quantum cryptography. She spent 22 years at Microsoft Research, as a Principal Researcher and Partner Research Manager of Cryptography and Privacy Research. She is an elected Fellow of the American Mathematical Society (AMS), the Society of Industrial and Applied Mathematics (SIAM), the Association for Women in Mathematics (AWM), and the American Association for the Advancement of Science (AAAS). PhD in Mathematics from The University of Chicago (1996). Affiliate Professor, University of Washington. Board of Trustees member, Mathematical Sciences Research Institute (MSRI, Berkeley). Former President, Association for Women in Mathematics (2015-2017).
TAG-DS is a hybrid seminar and will be available in-person at the UW Mathematics Department as well as online on Zoom. You can find the link to the Zoom meeting here. If you would like to be added to our mailing list, you can do so by visiting this page.