---
title: "Differential privacy"
description: "A mathematical guarantee that bounds how much any single person's record can change the output of an analysis or a trained model, tuned by a privacy budget."
canonical: https://aigovernanceengineer.com/glossary/differential-privacy
author: "Jorge García Aibar"
license: "CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/)"
doi: https://doi.org/10.5281/zenodo.22956197
version: "0.5.0"
updated: 2026-09-24
---

# Differential privacy

A mathematical guarantee that bounds how much any single person's record can change the output of an analysis or a trained model, tuned by a privacy budget. Its strength depends on the budget and on implementation choices that NIST calls privacy hazards [1].

- Developed in: [ch. 19, Privacy-enhancing technologies and their honest limits](https://aigovernanceengineer.com/bok/privacy-and-ai#privacy-enhancing-technologies-and-their-honest-limits)
- Chapters: [ch. 19, Privacy & AI](https://aigovernanceengineer.com/bok/privacy-and-ai)
- In the glossary chapter: https://aigovernanceengineer.com/bok/glossary#t-differential-privacy

## Sources

[1] NIST SP 800-226, Guidelines for Evaluating Differential Privacy Guarantees (differential privacy pyramid; privacy hazards). NIST. 2025-03. https://csrc.nist.gov/pubs/sp/800/226/final (verified: primary)