Official websites use .gov
A .gov website belongs to an official government organization in the United States.
Secure .gov websites use HTTPS
A lock (
) or https:// means you’ve safely connected to the .gov website. Share sensitive information only on official, secure websites.
Privacy-Preserving Federated Learning Blog Series
As a follow on to the past UK-US PETs Prize Challenges collaboration, we’re excited to share this joint blog series with our UK colleagues focused on federated learning, an approach that addresses the fundamental privacy challenge of traditional machine learning by avoiding the centralized collection of training data. We encourage readers to ask questions and contribute to our work. Please email us at PrivacyEng [at] nist.gov (PrivacyEng[at]nist[dot]gov) or pets [at] dsit.gov.uk (pets[at]dsit[dot]gov[dot]uk).
BLOG POSTS
The UK-US Blog Series on Privacy-Preserving Federated Learning: Introduction | December 7, 2023 | by Joseph Near, David Darais, Naomi Lefkovitz, and Dave Buckley
Privacy Attacks in Federated Learning | January 24, 2024 | by Joseph Near, David Darais, Dave Buckley, and Mark Durkee
Data Distribution in Privacy-Preserving Federated Learning | February 27, 2024 | by David Darais, Joseph Near, Dave Buckley, and Mark Durkee
Protecting Model Updates in Privacy-Preserving Federated Learning | March 21, 2024 | by Joseph Near and David Darais
Protecting Model Updates in Privacy-Preserving Federated Learning: Part Two | May 2, 2024 | by David Darais, Joseph Near, Mark Durkee, and Dave Buckley
Protecting Trained Models in Privacy-Preserving Federated Learning | July 15, 2024 | by Joseph Near and David Darais
Implementation Challenges in Privacy-Preserving Federated Learning | August 20, 2024 | by Joseph Near, David Darais, and Mark Durkee
Next blog post coming soon!