Google Research·· 2026-05-28
Private analytics via zero-trust aggregation
Private analytics via zero-trust aggregation
AI summary
Google combined a new single-message encrypted aggregation protocol with TEEs, letting devices submit without multiple online rounds. Google receives only anonymised group insights; raw data is neither exposed nor reconstructed even within hardware protection. TEE attestation proves execution follows public code.
Selection record
Threshold 60Official, first-handFirst 22Second 34
Not admittedSum of both 56 < twice the threshold 120
- Source tier
- Official, first-hand; this tier's threshold is 60
- Pre-filter
- passed：端侧AI隐私分析与安全聚合技术
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