Trail of Bits

ML / cryptography

MPC-learning

Multi-party computation library for machine-learning workflows built around a three-party protocol.

View on GitHub trailofbits/mpc-learning

Best for

Research contexts where privacy-preserving model computation matters.

Surface

ML / cryptography

Catalog group

Protect Python, packaging, and ML-heavy workflows

Repository

trailofbits/mpc-learning

From the README

MPC-learning is a Python library for performing multi-party computation on machine learning applications. This library implements the 3-party computation protocol of https://eprint.iacr.org/2016/768.pdf . For now, a "dealer" is required to distribute shares of inputs, and the protocol can only be run locally (does not support networking yet). This is a quick guide to getting this repo up and running for development.
Read the full README on GitHub ↗

Related tools · Protect Python, packaging, and ML-heavy workflows