Preprint
Sep 2026
Toward provably private learning from federated data
A next-generation FL system based on Trusted Execution Environments (TEEs) is presented that addresses operational challenges associated with earlier systems and provides externally verifiable central Differential Privacy (DP) guarantees for the first time while offering a better privacy-utility tradeoff.
Katharine Daly, Yu Xiao, Zachary Garrett et al.
· 0 citations