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
- Fickling Decompiler, static analyzer, and bytecode rewriter for Python pickle serializations.
- PrivacyRaven Privacy-testing library for deep-learning systems and privacy-preserving ML techniques.
- abi3audit Scans Python extensions and wheels for abi3 compatibility violations across package histories.
- CVEdb Library and CLI for consuming NVD data directly without leaning on third-party APIs.