Microsoft Research
CompanyMicrosoft Research (MSR) is the research subsidiary of Microsoft. It was created in 1991 by Richard Rashid, Bill Gates and Nathan Myhrvold with the intent to advance state-of-the-art computing and solve difficult world problems through technological innovation in collaboration with academic, government, and industry researchers. Microsoft Research employs more than 1,000 computer scientists, physicists, engineers, and mathematicians, including Turing Award winners, Fields Medal winners, MacArthur Fellows, and Dijkstra Prize winners.
From Wikipedia, licensed under CC BY-SA 4.0. Shown as published there.
Facts
- Country
- United StatesSource: Wikidata
- Founded
- 1991Source: Wikidata
- Founded by
- Bill GatesSource: Wikidata
- Parent company
- MicrosoftSource: Wikidata
- Headquarters
- RedmondSource: Wikidata
- Subsidiaries
- Microsoft Ireland Research, Microsoft Research (Germany), Microsoft Research Asia, Microsoft Research India, Microsoft Research, United KingdomSource: Wikidata
- Wikipedia
- Read on WikipediaSource: Wikidata
Recent news
Microsoft researchers show a few altered neurons can plant a date-triggered backdoor in an LLM
Microsoft Research describes a technique called Lazarus that rewrites fewer than 10 dormant neurons in an open-weight model's final feed-forward layer, so an agent built on it emits attacker commands on a trigger such as a date change, without retraining. On Nemotron-Terminal-8B, seven neurons were enough, with the payload generated in at least 98.8% of held-out trigger cases and no activation in benign tests. Microsoft Threat Intelligence has not observed threat actors using it and advises auditing weights, verifying provenance and restricting agent permissions.
Microsoft Research shows AI model neurons can be edited to hide sleeper agent backdoors
Microsoft Research describes a backdoor in which editing fewer than 10 neurons turns a capable agent model into a sleeper agent that passes evaluations but executes an attacker's command when a trigger string appears in its context. Because agents often run unattended with privileged access, model weight integrity matters for both third-party and internally built models. Microsoft has not observed threat actors using the technique, and says frontier agents can detect anomalous weight edits.