Safety, Ethics & Governance · advanced · concept 290 of 311 · Updated Nov 4, 2026
Differential Privacy & ML Privacy
A mathematical guarantee that a model or statistic barely changes whether or not any single person's data is included, enforced by adding calibrated noise. The gold standard for training on sensitive data, used by the US Census, Apple, and Google, with a real accuracy cost to budget for.
Top AI contributors on this
- Fei-Fei LiWorld Labs / Stanford University
- Timnit GebruDistributed AI Research Institute (DAIR)
- Margaret MitchellHugging Face
- Sara HookerAdaption Labs
- Yejin ChoiStanford University
- Yi ZengBeijing Institute of AI Safety and Governance / Renmin University of China
Key terms
Privacy budget (epsilon)Noise injectionDP-SGDMembership inferenceAnonymization limits
Learn these first
Where you meet it in the real world
US Census releases, keyboard prediction telemetry, medical research on patient data
Videos
▶ Tutorial: Differential Privacy and Learning: The Tools, The Results, and The Frontier ↗
Microsoft Research · YouTube
▶ Differential Privacy for Growing Databases ↗
Microsoft Research · YouTube
Guides and articles
Courses, papers, and more