Running Numpy programs homomorphically

Zama will present some of its work on homomorphic data science at the next meetup.

Making Fully Homomorphic Encryption mainstream requires developing tools that make it easy to use for non-cryptographers. Being able to take regular Numpy programs and run them on encrypted data would enable data scientists to integrate FHE into their models, however complex they might be.

At the next meetup on September 30th, our team will showcase an experimental version of a homomorphic compiler for Numpy, including a live coding session where they will implement a homomorphic recurrent network for sentiment analysis. is an open community of researchers and developers interested in privacy preserving techniques such as homomorphic encryption. With more than 1300 people, it is the largest community dedicated to FHE.

If you’d like to attend the online meetup, sign up here.

About the speakers

Dr Rand Hindi is an entrepreneur and investor in deeptech. He is the CEO at Zama, and was formerly the CEO at Snips (acquired by Sonos in 2019). Rand is an investor in 30+ companies across cybersecurity, AI, blockchain, psychedelics and medtech. He holds a PhD in bioinformatics from UCL.

Samuel Tap is a doctoral researcher at Zama and INRIA, working on homomorphic compilation. He was the first hire at Zama, where he was originally working on cryptography research and the Concrete framework.

Ayoub Benaissa is a cryptography engineer at Zama focusing on homomorphic compilation. He was previously working with OpenMined, where he developed TenSEAL, a python library for homomorphic encryption.