Distributed AI is one of the most important topics of privacy preserving computation. Here is a recently published library:
Paper by Sathya, et.al.
Good overview with comments on available homomorphic encryption libraries.
Microsoft has published their “Simple Encryoted Arithmetic Library” SEAL. The code is written in standard c++ without external dependencies.
Microsoft has lead international efforts to standardize homomorphic encryption. Standardization and a larger base of developers actually working on this new paradigm of provacy-preserving computation are key to turn homomorphic encryption from an experimental, academic research into applications that can practically be implemented for real use cases.
Read Microsofts anouncement here:
The SEAL repo on Gitub:
Very useful code to evaluate homomorphic encryption accross different schemes:
Rust library for the Paillier partially homomorphic encryption scheme, offering also packed encoding for encrypting several values together as well as several zero-knowledge proofs related to typical use-cases. Supports several underlying arbitrary precision libraries, including RAMP and GMP.
Several companies have invested resources in the development of this library, including Snips who implemented the original version for use in their privacy-preserving analytics system, and KZen networks who contributed with implementations of many zero-knowledge proofs. See contributions below for more details.
Important: while we have followed recommendations regarding the scheme itself, some parts of this library have not yet been harden against non-cryptographic attacks such as side-channel attacks.