The U.S. National Institute of Standards and Technology published guidance on privacy-preserving federated learning systems that are vertically partitioned. The guidance discusses different aspects of implementing vertical PPFL systems while taking steps to balance "the privacy risk of information leakage against the performance cost of preventing" data leaks.
NIST publishes guidance on privacy-preserving federated learning systems
Related stories
Privacy in the age of robotics: A discussion with Erin Relford
GPS 2025: Sam Altman, Alex Blania discuss Tools for Humanity's biometric technology
Notes from the IAPP Canada: An evolving approach to privacy amid geopolitical shifts
GPS 2025: European regulators reflect on pay or consent enforcement, concerns
GPS 2025: Collaboration, precision highlight future of US state privacy law enforcement