Read the latest publications by the people at Zama

want to Join our research team?

See the job openings

December 2022

Parameter Optimization and Larger Precision for (T)FHE


Loris Bergerat, Anas Boudi, Quentin Bourgerie, Ilaria Chillotti, Damien Ligier, Jean-Baptiste Orfila, Samuel Tap

To appear

SEPTEMBER 2022 — CHES

SoK: Fully homomorphic encryption over the [discretized] torus

Marc Joye

To appear

SEPTEMBER 2022 — SCN

Scooby: Improved multi-party homomorphic secret sharing based on FHE

Ilaria Chillotti, Emmanuela Orsini, Peter Scholl, Nigel Smart, and Barry Van Leeuwen

To appear

June 2022 — CSCML

Blind rotation in fully homomorphic encryption with extended keys

Marc Joye and Pascal Paillier

Read paper

December 2021 — ASIACRYPT

Balanced non-adjacent forms





— Marc Joye

Read paper

December 2021 — ASIACRYPT

Improved programmable bootstrapping with larger precision and efficient arithmetic circuits for TFHE

Ilaria Chillotti, Damien Ligier, Jean-Baptiste Orfila, and Samuel Tap

Read paper

July 2021 — CSCML

Programmable bootstrapping enables efficient homomorphic inference of deep neural networks

— Ilaria Chillotti, Marc Joye, and Pascal Paillier

Read paper

December 2020 — WAHC

CONCRETE: Concrete Operates oN Ciphertexts Rapidly by Extending TfhE



— Ilaria Chillotti, Marc Joye, Damien Ligier, Jean-Baptiste Orfila, and Samuel Tap

Read paper

December 2020 — PPML

New challenges for fully homomorphic encryption


— Ilaria Chillotti, Marc Joye, and Pascal Paillier

Read paper

august 2020 — USENIX

SANNS: Scaling up secure approximate k-nearest neighbors search


Hao Chen, Ilaria Chillotti, Yihe Dong, Oxana Poburinnaya, Ilya Razenshteyn, and M. Sadegh Riazi

Read paper

We’re building
products to make
FHE programming
fast and easy

Concrete Numpy

Concrete Numpy is an open-source set of tools which aims to simplify the use of fully homomorphic encryption (FHE) for data scientists.

RESOURCES

Explore more content about the Concrete Numpy library

Announcing Concrete ML v0.2

We are announcing the release of Concrete ML as a public alpha. The package is built on top of Concrete Numpy.

Read Article

Quantization of Neural Networks for Fully Homomorphic Encryption

Machine Learning and the Need for Privacy‍

Read Article

Privacy-preserving insurance quotes

A tutorial on how to build an FHE-enabled insurance incident predictor.

Read Article

Hummingbird

Concrete Numpy is an open-source set of tools which aims to simplify the use of fully homomorphic encryption (FHE) for data scientists.

RESOURCES

Explore more content about the Hummingbird library

Announcing Concrete ML v0.2

We are announcing the release of Concrete ML as a public alpha. The package is built on top of Concrete Numpy.

Read Article

Quantization of Neural Networks for Fully Homomorphic Encryption

Machine Learning and the Need for Privacy‍

Read Article

Privacy-preserving insurance quotes

A tutorial on how to build an FHE-enabled insurance incident predictor.

Read Article