Security, privacy, and cryptography
Video
Differentially Private Synthetic Data without Training
Generating differentially private (DP) synthetic data that closely resembles original data while preserving user privacy is a scalable solution to address privacy concerns in today’s data-driven world. In this talk, I will introduce Private Evolution…
Project
National AI Research Resource (NAIRR) Pilot
Microsoft is delighted to contribute as a lead supporter of the National AI Research Resource (NAIRR) pilot. (opens in new tab) The mission of the NAIRR pilot aligns with our commitment to broaden AI research…
Video
Attestations over TLS 1.3 and ZKP
The Transport Layer Security (TLS) protocol is fundamental for securing data transmission over the Internet, providing encrypted and authenticated channels that protect users’ data. However, certain scenarios require not only secure transmission but also the…
Publication
Inferentially-Private Private Information
Microsoft Research Blog
Research Focus: Week of January 13, 2025
In this edition: Privacy enhancements for multiparty deep learning; using smaller, open-source models to provide relevance judgments; new tool uses AI, data to automate innovation and development; Yasuyuki Matsushita named IEEE 2025 Computer Society Fellow.
