Home | Resources | Meetups | Conference 2025 | Join the community

---

Concrete ML - Machine Learning on Encrypted Data

by Andrei Stoian - 2024.09.26 5PM CEST

Video recording (Youtube) | Slides (Github) | Join the discussion (Discord)

Abstract

Concrete ML is an open-source framework developed by Zama, that enables AI to use Fully Homomorphic Encryption (FHE). It gives developers a way to convert their machine learning models to use FHE through a straightforward and familiar programming interface. and supports all popular machine learning models, including boosted trees, neural networks and large language-models (LLMs). Concrete ML lowers the barrier for adoption of privacy preserving machine learning by removing the need for ML developers to have any cryptography knowledge.

About the speaker

Andrei obtained an Engineering degree in Computer Systems from the Politehnica University of Bucharest, then a PhD in Machine Learning for image and video analysis at the Conservatoire National des Arts et Metiers in Paris, France, in 2015. Since 2021 he has been working for Zama on building Concrete-ML, a machine learning toolkit to perform model inference on encrypted data. His research interests are centred on adapting deep learning models to FHE computation, especially in the areas of image classification and recognition. He has published more than 20 papers on various machine learning topics and holds several patents.

Register for meetup

If you’d like to RSVP for the meetup via meetup.com, click here.

Never miss an update

The newsletter where we post community announcements: https://fheorg.substack.com/

The discord server where you can discuss FHE related topics with the community: https://discord.fhe.org

Make sure to join either (or both) of these to stay informed about future events!