Originally published 280224
The UK Responsible Technology Adoption Unit (RTAU) and the US National Institute of Standards and Technology (NIST) have released the first joint article in a new series explaining the concept of federated learning and how it differs from traditional centralised learning methods. Federated learning involves distributing data among participating organisations and sharing model updates instead of raw data. NIST's post explores the different ways data can be partitioned among participants in federated learning systems and discusses techniques for building privacy-preserving systems. The series will continue with future posts which will describe specific techniques for each situation.
A follow-up article in their series explaining the concept of federated learning and how it differs from traditional centralised learning methods. The latest article explores the various aspects of vertical privacy-preserving federated learning systems, including bloom filters and balancing performance with leakage.
What is this page?
You are reading a summary article on the Privacy Newsfeed, a free resource for DPOs and other professionals with privacy or data protection responsibilities helping them stay informed of industry news all in one place. The information here is a brief snippet relating to a single piece of original content or several articles about a common topic or thread. The main contributor is listed in the top left-hand corner, just beneath the article title.
The Privacy Newsfeed monitors over 300 global publications, of which more than 5,750 summary articles have been posted to the online archive dating back to the beginning of 2020. A weekly roundup is available by email every Friday.
