Google's TEE-based federated learning system adds verifiable privacy guarantees
Toward provably private learning from federated data
Google announces a next-generation federated learning system that uses Trusted Execution Environments to provide verifiable, auditable data anonymization. The system publishes access policies to a public transparency log and is deployed in Gboard, which has launched English and Japanese next-word prediction models with stronger privacy guarantees and improved accuracy. Training time has also sped up significantly because computation moved to the server and is parallelized across many machines.
The post shows how Trusted Execution Environments make federated learning's privacy claims externally verifiable, rather than relying on trust in the server operator.
Source: Google Research · research.google