Gboard (Product): news timeline & CVEs

Google Research Moves Federated Learning Into TEEs: Gboard Now Trains With Externally Verifiable Differential Privacy

Google moved Gboard federated learning into attested TEEs with externally verifiable differential privacy.

Google Research described a federated learning design that computes gradients in attested server-side trusted execution environments instead of on phones. Access policies are published to Sigstore's Rekor transparency log and binaries are reproducibly buildable, so central differential privacy can be checked externally. Gboard already uses the system for English and Japanese next-word prediction.

MarkTechPostOct 4, 07:29 UTC · 5d agoAI research1

Toward verifiably private learning from federated data

A TEE-based federated learning system trains Gboard models faster under smaller, verifiable privacy budgets.

The paper describes a TEE-based federated learning system in which devices upload data encrypted under keys from a TEE-hosted key management service. Uploads are cryptographically bound to policies that limit which Python programs may process them in server-side TEEs, and outsiders can inspect transparency logs of allowed workloads. The authors report better device coverage and privacy-utility tradeoffs because data can be incorporated on a schedule that optimizes differential privacy rather than device availability. The system is productionized for Android Keyboard (Gboard), training models faster with better accuracy under smaller, externally verifiable privacy budgets than the prior system.

arXiv cs.CRSep 25, 16:34 UTC · 13d agoResearch

Gboard

Timeline2 articles

Appears with

Google Research Moves Federated Learning Into TEEs: Gboard Now Trains With Externally Verifiable Differential Privacy

Toward verifiably private learning from federated data