Federated Learning in 10 Lines of code, with PySyft

In our last post, we ran a machine learning experiment using PySyft to study heart disease. Now, we’ll enhance that by implementing a Federated Learning example with the same medical datasets. The best part? We can do this in just 10 lines of code, thanks to a new gem in the PySyft API!

Beginner Friendly Terminology

A gentle introduction to Deep Learning and its associated terms along with Implementation in Tensorflow and Keras. - Part 1 What is Deep Lea

Confidential Computing Explained. Part 2 : Attestation

This post introduces the concept of attestation with Intel SGX enclaves

Confidential computing explained. Part 1: introduction

This post is a first introduction to the basic principles of Confidential Computing.

Tempered Sigmoid Activations for Deep Learning with Differential Privacy

Read to find out how tempered sigmoid activations help overcome the problem of exploding gradients and yield better accuracy under differentially private model training.

PrivacyRaven: Comprehensive Privacy Testing for Deep Learning

Access to only the output labels is a seemingly restrictive setting. What is an adversary modeled by PrivacyRaven capable of, given this restrictive setting?

How to setup PySyft on Windows 10

In this tutorial, you are going to learn how to setup PySyft, a privacy-preserving machine learning framework, on Windows 10.

How GANs can cause a Privacy Breach in Federated Deep Learning

Research has shown that it is possible to launch an attack where a malicious user uses Generative adversarial network (GANs) to recreate sam

Sentiment Analysis on Multiple Datasets With SyferText - Demo

How can you do pre-processing if you are not allowed to have access to plaintext data? SyferText can help you! With SyferText, you can define pre-processing components to perform pre-processing remotely, blindly and in a completely secure fashion.

Towards privacy with RStudio: Encrypted deep learning with Syft and Keras

In this post, we introduce Syft, an open-source framework that integrates with PyTorch as well as TensorFlow, and show how to use it from R. In an example use case, we obtain private predictions from an R Keras model.

Predictive Maintenance of Turbofan Engines using Federated Learning with PySyft and PyGrid

Is it possible to benefit from the wonders of machine learning without having direct access to data? Today, machine learning can be used to

Introduction to Federated Learning and Privacy Preservation using PySyft and PyTorch

Federated Learning and Additive Secret Sharing using the PySyft framework

Split Neural Networks on PySyft and PyTorch

Update as of November 18, 2021: The version of PySyft mentioned in this post has been deprecated. Any implementations using this older versi

Meet OpenMined's new PyTorch-OpenMined Fellows

We’re very excited to announce the recipients of the latest round of open-source software development grants in the OpenMined community, gen

Introducing PySyft TensorFlow

Support for TensorFlow in PySyft!

Asynchronous Federated Learning in PySyft

Update as of November 18, 2021: The version of PySyft mentioned in this post has been deprecated. Any implementations using this older versi

Privacy-Preserving AI in Medical Imaging: Federated Learning, Differential Privacy, and Encrypted Computation

In medical imaging, necessary privacy concerns limit us from fully maximizing the benefits of AI in our research. These modern privacy techniques could allow us to train our models on encrypted data from multiple institutions, hospitals, and clinics without sharing the patient data.

Encrypted Training with PyTorch + PySyft

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

Federated Learning of a Recurrent Neural Network on Raspberry PIs

In this article, you are going to learn how to setup PySyft on a Raspberry PI and how to train a Recurrent Neural Network in a federated way.

Encrypted Deep Learning Classification with PyTorch & PySyft

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