A Survey of Differential Privacy Frameworks

A comprehensive overview of various libraries and frameworks for differential privacy and their use cases.

Case Study - Federated privacy preserving analytics for secure collaboration among Telco and partners to improve customer engagement

MotivationWhile consumers expect better customer experience and personalization from businesses, they are increasingly sensitive to privacy

Design a federated learning system in seven steps

What should you consider when building an enterprise federated learning system?Photo by Hunter Harritt on UnsplashIntroductionCompanies like

Making autonomous vehicles robust with active learning, federated learning & V2X communication

When we think of driving in general, there are good drivers and bad drivers. So, on a 2D spectrum, we would picture a cluster of data of those drivers and realise that the good drivers’ data is clustered around a particular coordinate(x,y) while the bad drivers’ data is all over the place.

Installing PySyft v0.5.0 with PyGrid on a Raspberry Pi 4

Introduction Install PySyft PyTorch v1.8.1 (1 min) Install other dependencies (6 min) Install syft 0.5.0 (6 min) Testing the environment In

Adaptive Federated Optimization

In non-federated settings, adaptive optimization methods have desirable convergence properties. Can federated versions of these adaptive optimizers, including Adagrad, Adam, and Yogi facilitate better convergence in the presence of heterogeneous data?

Advances and Open Problems in Federated Learning

What are some of the recent advances in Federated Learning? What challenges do the privacy principles guiding Federated Learning (FL) bring into the system?

What's in the TensorFlow Federated (TFF) box?

TensorFlow Federated (TFF) is a new development framework for Federated Computations (FC). Here's a summary of TFF's design goals and capabilities.

Private Deep Learning of Medical Data for Hospitals using Federated Learning and Differential privacy

Featuring Dmitrii Usynin - Speaker at #PriCon2020 - Sept 26 & 27 With the upcoming OpenMined Private Conference 2020 around the corner

Understanding the Types of Federated Learning

In this article I’ll attempt to untangle and disambiguate some terms that have emerged to describe different Federated Learning scenarios.

Speech Command Prediction with Federated Learning

Photo by Jason Rosewell on UnsplashUpdate as of November 18, 2021: The version of PySyft mentioned in this post has been deprecated. An

Three Ways to Future-Proof your Data Analytics against the Changing Regulatory Landscape

On July 16, the ECJ invalidated the EU-US Privacy Shield, one of the key mechanisms for lawfully transferring data between the EU and the US. Federated Learning and other Privacy Preserving techniques would help solve some of the new challenges organizations face.

Announcing 4 New Libraries for Federated Learning on Web and Mobile Devices

As part of the PyTorch/OpenMined grants we announced last December, the Web & Mobile team has been hard at work on developing 4 new libraries for model-centric federated learning.

Announcing the OpenMined-UCSF Data-Centric Federated Learning Fellowship

We’re very excited to announce the next round of open-source software development grants in the OpenMined community, generously sponsored by the University of California San Francisco! These grants will focus on bringing data-centric federated learning with differential privacy budgeting to PyGrid.

Federated Learning for Credit Scoring

Want bureaus to score your credit without hoarding your data? Find out how FL can enable privacy-preserving, cross-border credit assessment.

A Federated Learning Approach for Pill Identification

Alright, so you’ve built an MNIST classifier using Federated Learning. Now it’s time to build something a little more cooler. Let’s build a

Privacy-Preserving Data Science, Explained

In this blog series, we’ll explain common topics in privacy-preserving data science, from a single sentence to code examples. We hope these posts serve as a useful resource for you to figure out the best techniques for your organization.

What is Federated Learning?

This post is part of our Privacy-Preserving Data Science, Explained series. Update as of November 18, 2021: The version of PySyft mentioned

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

OpenMined + apheris AI Partnership for PyTorch Mobile Federated Learning

Today, we’re very excited to announce our Use Case partnership with apheris AI to deploy the very first open-source system for private federated learning on server, web, and mobile at scale.

Introduction to Federated Learning and Privacy Preservation using PySyft and PyTorch

Federated Learning and Additive Secret Sharing using the PySyft framework

Announcing the OpenMined-PyTorch Federated Learning Fellowships

We’re very excited to announce the next round of grants sponsored by the PyTorch team! This grant will focus on developing “worker libraries”, allowing PySyft code to be executed in other environments like a mobile phone or web browser.

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