Machine LearningCybersecurity8 min reading time

Toward provably private learning from federated data

Google Research Blog
Read the full article
Google has developed a next-generation federated learning system using Trusted Execution Environments (TEEs) to enhance data anonymization with verifiable and auditable privacy guarantees. This new system improves privacy and accuracy while reducing compute times, already benefiting Gboard's predictive features.

More in Machine Learning

Machine Learning2 min read

Google rolls out new Gemini AI model but restricts access over safety concerns

Covered by 11 sources
Machine Learning4 min read

Ai2 releases Olmo-core 3 to make developing large mixture-of-experts LLMs more efficient

Covered by 3 sources
Machine Learning3 min read

Robotics startup FieldAI is set to raise $700 million at a $10 billion valuation

Covered by 2 sources