PySyft + Opacus: Federated Learning with Differential Privacy

We use Opacus from PyTorch and PySyft from OpenMined to combine Federated Learning with Differential Privacy.

Encrypted Inference using ResNet-18

Encrypted inference with ResNet-18 using PyTorch + PySyft on ants & bees images

CrypTen Integration into PySyft

CrypTen integrated in PySyft: a fast SMPC backend for secure computation between servers.

What is Secure Multi-Party Computation?

This post is part of our Privacy-Preserving Data Science, Explained Simply series.

Genetic data privacy in the dawn of big data forensics

“You would see hundreds and hundreds of unsolved crimes solved overnight,” Detective Michael Fields of the Orlando Police Department, from

Announcing the OpenMined-PyTorch for Crypten Integration Fellowships

We’re very excited to announce the next round of open-source software development grants in the OpenMined community, generously sponsored by

Encrypted Training with PyTorch + PySyft

Encrypted Training of Deep Learning models with PyTorch + PySyft on MNIST

Encrypted Deep Learning Classification with PyTorch & PySyft

Encrypted Deep Learning Classification with PyTorch & PySyft in < 33ms on MNIST

Deep Learning -> Federated Learning in 10 Lines of PyTorch + PySyft

Deep Learning -> Federated Learning in 10 Lines of PyTorch + PySyft