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

MPyC: Multiparty Computation in Python

A privacy preserving NLP framework

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.

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.

Fault-tolerant secure multiparty computation in Python.

Collaboration project with Criteo in order to evaluate the relevance of the Secure Multiparty Computation (sMPC) in the context of a Federative Learning

Data structure for representing additive secret shares of integers, designed for use within secure multi-party computation (MPC) protocol implementations.

Oblivious transfer (OT) communications protocol message/response functionality implementations based on Curve25519 and the Ristretto group.

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

Extremely Randomized Trees with Privacy Preservation for Distributed Data (k-PPD-ERT)

A Python 🐍 Secure Multi-Party Computation Sandbox with a Joint Signature Scheme using Elliptic Curve Cryptography ✉️+🔑+🔑+🔑 = 🔓

Secure Aggregation with Shamir’s Method

MPC management framework automating a secure network setup among participants of multiparty computation in the outsourced setting.

Specification of the Mastic Verifiable Distributed Aggregation Function (VDAF)

MPC management framework automating a secure network setup among participants of multiparty computation in the outsourced setting.

Data structure for representing secret shares of byte vectors based on bitwise XOR, designed for use within secure multi-party computation (MPC) protocol implementations.