Privacy Preserving Machine Learning with Fully Homomorphic Encryption

A Google TechTalk, presented by Jordan Fréry, 20230117 ABSTRACT: In today s digital age, protecting privacy has become increasingly difficult. However, new developments such as Fully Homomorphic Encryption (FHE) provide a means of safeguarding sensitive client information. We are excited to present ConcreteML, our opensource library that allows for the seamless conversion of Machine Learning (ML) models into their FHE counterparts. With our technology, clients can enjoy zerotrust interactions with service providers while also enabling the deployment of ML models on untrusted servers without compromising the privacy of user data. Jordan Fréry is a research scientist at Zama