Google Research·· 14 d ago
Toward provably private learning from federated data
Toward provably private learning from federated data
AI summary
In “Toward provably private learning from federated data”, we announce the next generation of our FL system, which leverages Trusted Execution Environments (TEEs) to provide verifiable and auditable guarantees for data anonymization. Gboard has adopted the system to launch next-word prediction models in English and Japanese, with stronger privacy guarantees and improved accuracy.
Selection record
Threshold 60Official, first-handFirst 62Second 62
AdmittedSum of both 124 ≥ twice the threshold 120
- Source tier
- Official, first-hand; this tier's threshold is 60
- Pre-filter
- passed：联邦学习与TEE隐私AI系统技术介绍
- Why it was chosen
- Google has published the design of its next-generation TEE-based federated learning system, showing how the data anonymization process can be made externally verifiable.
A model scores each item twice, independently, against one written standard, out of 100. An item is admitted only when the two scores add up to twice the threshold. The threshold is set per source tier.
Source: Google Research · research.google