A unified framework for privacy-preserving data analysis and machine learning

Versatile framework for multi-party computation

This is the development repository for the OpenFHE library. The current version is 1.3.1 (released on July 11, 2025).

A Privacy-Preserving Framework Based on TensorFlow

MPyC: Multiparty Computation in Python

SPU (Secure Processing Unit) aims to be a provable, measurable secure computation device, which provides computation ability while keeping your private data protected.

A privacy preserving NLP framework

Synergistic fusion of privacy-enhancing technologies for enhanced privacy protection.

Kuscia(Kubernetes-based Secure Collaborative InfrA) is a K8s-based privacy-preserving computing task orchestration framework.

Cloud native Secure Multiparty Computation Stack

HEonGPU is a high-performance library that optimizes Fully Homomorphic Encryption (FHE) on GPUs. Leveraging GPU parallelism, it reduces computational load through concurrent execution. Its multi-stream architecture minimizes data transfer overhead, making it ideal for large-scale encrypted computations with reduced latency.

Minimal pure-Python implementation of a secure multi-party computation (MPC) protocol for evaluating arithmetic sum-of-products expressions via a non-interactive computation phase.

Python library that serves as an API for common cryptographic primitives used to implement OPRF, OT, and PSI protocols.

Updatable Private Set Intersection Revisited: Extended Functionalities, Deletion, and Worst-Case Complexity (Asiacrypt 2024)

Secure Computation Utilities

Curl: Private LLMs through Wavelet-Encoded Look-Up Tables

Minimal pure-Python implementation of Shamir's secret sharing scheme.

Secure Federated Learning Framework with Encryption Aggregation and Integer Encoding Method.

SecretFlow-Serving is a serving system for privacy-preserving machine learning models.

TypeScript library for working with encrypted data within nilDB queries and replies.