This month, our team at Zama released TFHE-rs, the fastest public implementation of the TFHE scheme, alongside new updates for its Concrete ML and Concrete Numpy libraries. With these releases, Zama continues to build its suite of products to make fully homomorphic encryption accessible, easy, and fast.
TFHE-rs
This library is a pure Rust implementation of TFHE for booleans and small integer arithmetics over encrypted data. This is the new reference implementation for TFHE by extending the usual scheme possibilities, including up-to-date security parameters and state-of-the-art features.
Read the full announcement blog post here.
Concrete Numpy v0.9
This version of Concrete Numpy adds many new updates to our library: a compiler update that improves performance, 16-bits integer table lookups, and many other new features.
Read the full announcement blog post here.
Concrete ML v0.6
This version of Concrete-ML adds new and exciting features such as fast, high-precision linear models and support for 16-bit accumulators for both built-in and custom neural nets have been added.