AI Briefing#privacy-preserving-ml
The latest AI and developer news about #privacy-preserving-ml, with the original source and a short summary.
The latest AI and developer news about #privacy-preserving-ml, with the original source and a short summary.
Shortens Gboard training period from 2 months to 3 weeks and improves privacy budget by 3x
Microsoft Research scientists Jennifer Neville and Chad Atalla discuss how AI models degrade in multi-turn interactions despite high single-turn benchmark scores, highlighting the need for new evaluation methods and user strategies.
OpenMed 2.0, an open-source NLP stack for protecting medical data, has been released with multilingual PHI de-identification capabilities.
Introduces how to perform Transformer-based sentiment analysis on encrypted data using Concrete-ML.