Encyclopedia · 176 concepts

Safety, Ethics & Governance · advanced · concept 176 of 176

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.

Key terms

Privacy budget (epsilon)Noise injectionDP-SGDMembership inferenceAnonymization limits

Where you meet it in the real world

US Census releases, keyboard prediction telemetry, medical research on patient data