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

A Fully Homomorphic Encryption (FHE) library for bridging the gap between theory and practice with a focus on performance and accuracy.

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

A Homomorphic Encryption-Driven Python Framework for Secure Cloud-Based Facial Recognition

Flower framework for Federated Learning, with Fully Homomorphic Encryption integrated

A CKKS implementation in SageMath which supports basic bootstrapping.

Privacy-preserving LLM inference with CKKS homomorphic encryption and Private Linear Layer (PLL) protection for LoRA fine-tuned models

several implementations of the number theoretic transform (NTT)

Experiments in using Z3 to check common FHE transformations

mcp server based on the new homomorphic encryption technology "ZionFHE"

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

Advanced RAG (Retrieval-Augmented Generation) powered chatbot that provides instant, accurate answers about Zama Protocol's Fully Homomorphic Encryption (FHE) technology

Privacy-preserving disease risk prediction using the CKKS homomorphic encryption scheme.

Experiments in FHE and zkLLMs during Sage Bionetworks 2025 AI hackathon

ACM Summer School 2025: Introduction to Cryptography