Advancing Private AI Compute with secure, server-side memory
Advancing Private AI Compute with secure, server-side memory
Google DeepMind announced an update to Private AI Compute that brings persistent, cross-device AI memory to the cloud while maintaining device-level privacy standards. Data is sealed in encrypted storage, with decryption keys retained only on user devices. When a model needs access, an end-to-end encrypted channel connects to a cloud secure enclave, where data is temporarily decrypted in isolated memory, then re-encrypted immediately after new context is saved.
Selection record
AdmittedSum of both 124 ≥ twice the threshold 120
- Source tier
- Official, first-hand; this tier's threshold is 60
- Pre-filter
- passed：Google私有AI计算架构技术更新
- Why it was chosen
- Google's encryption and verification design shows how cross-device AI memory can be implemented under privacy constraints.
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 DeepMind · deepmind.google