New Privacy-Preserving Federated Learning Blog Post!
Dear Colleagues,
ln our last Privacy-Preserving Federated Learning (PPFL) post, we explored the problem of providing input privacy in PPFL systems for the horizontally-partitioned setting. In this new post, Protecting Model Updates in Privacy-Preserving Federated Learning: Part Two, we focus on techniques for providing input privacy when data is vertically partitioned. This is particularly challenging, and organizations will need to grapple with trade-offs between data leakage and performance costs. Learn more in the fifth post of our series.
Protecting Model Updates in Privacy-Preserving Federated Learning: Part Two by David Darais, Joseph Near, Mark Durkee, and Dave Buckley
Read blogs #1 – #5 on our PPFL Blog Series page. We encourage readers to ask questions by contacting us at [email protected].
Meanwhile—stay tuned for the next PPFL blog post!
All the best,
NIST Privacy Engineering Program