Ground Truth.
AI, checked against the source.

← All topics

federated-learning

Everything on Ground Truth tagged “federated-learning” — 2 items.

Gboard now trains its next-word models on encrypted uploads inside auditable sealed hardware News

Google says Gboard's English and Japanese next-word models now train on encrypted phone data processed only inside attested trusted execution environments, with the allowed code published to a public log for outside auditors.

Confidential Federated Compute Tool

Google's open-source server code and audit guides for running federated learning and analytics workloads inside attested trusted execution environments, as now used for Gboard model training.