Security, privacy, and cryptography
Project
Project Roma
Deterministic security for AI agents AI agents perform consequential actions while processing data from various sources, including trusted collaborators and the public Web. It is crucial that AI agents handle this data with care: confidential…
Microsoft Research Blog
Project Ire autonomously identifies malware at scale
Designed to classify software without context, Project Ire replicates the gold standard in malware analysis through reverse engineering. It streamlines a complex, expert-driven process, making large-scale malware detection faster & more consistent.
Project
Project Ire
Autonomous malware classification Project Ire is an LLM-powered autonomous malware classification system. For inquiries, please direct mail to: ireinquiries@service.microsoft.com
Video
Precio: Private Aggregate Measurement via Oblivious Shuffling
This talk presents Precio, a secure aggregation system for computing layered histograms and sums over secret shared data in a client-server setting. Precio is motivated by private ad measurement scenarios, where online advertisers and ad…
