This post is a summary of this video titled: Privacy Preserving Machine Learning with Fully Homomorphic Encryption, done by Jordan Fréry.
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 Concrete-ML, our open-source library that allows for the seamless conversion of Machine Learning (ML) models into their FHE counterparts. With our technology, clients can enjoy zero-trust interactions with service providers while also enabling the deployment of ML models on untrusted servers without compromising the privacy of user data.
Concrete-ML (make the internet safe): https://github.com/zama-ai/concrete-ml