Concrete ML: Privacy Preserving ML framework using Fully Homomorphic Encryption (FHE), built on top of Concrete, with bindings to traditional ML frameworks.

Develop on and interact with BasedAI.

Official mirror of Python-FHEz; Python Fully Homomorphic Encryption (FHE) Library for Encrypted Deep Learning as a Service (EDLaaS).

Python implementation of the Fully Homomorphic Encryption Scheme TFHE

Flower framework for Federated Learning, with Fully Homomorphic Encryption integrated

Official code for "DCT-CryptoNets: Scaling Private Inference in the Frequency Domain" [ICLR 2025]

Fully Homomorphic Encryption for Private Federated Learning

Cifer provides a decentralized AI development ecosystem with data-ownership proof on the Cifer blockchain, using a Privacy-Preserving Machine Learning (PPML) framework offers several methods for secure, private, collaborative machine learning “Federated Learning” and “Fully Homomorphic Encryption”

This is an attempt to use BFV-FHE scheme for image encryption using an open-source implementation of the same.

The first one in the World fast, secure and practical Fully Homomorphic Encryption (FHE) cryptosystem. So far, here I place only demo samples, since all the algorithms and implementation are proprietary

A Privacy-Preserving Federated Learnig benchamarking framework, based on TensorFlow/Keras and OpenFHE

Experiments in using Z3 to check common FHE transformations

MPC key storage experiments for various FHE cryptosystems using Nillion's nilDB