You are viewing this page in an unauthorized frame window. This is a potential security issue, you are being redirected to https://csrc.nist.gov . An official website of the United States government Here’s how you know Here’s how you know Official websites use .gov A .gov website belongs to an official government organization in the United States. Secure .gov websites use HTTPS A lock ( Lock Locked padlock icon ) or https:// means you’ve safely connected to the .gov website. Share sensitive information only on official, secure websites. Search Search CSRC MENU Search Search Projects Publications Expand or Collapse Drafts for Public Comment All Public Drafts Final Pubs FIPS (standards) Special Publications (SP s ) IR (interagency/internal reports) CSWP (cybersecurity white papers) ITL Bulletins Project Descriptions Journal Articles Conference Papers Books Topics Expand or Collapse Security & Privacy Applications Technologies Sectors Laws & Regulations Activities & Products News & Updates Events Glossary About CSRC Expand or Collapse Computer Security Division Cryptographic Technology Software Security Group Hardware Security Group Security Engineering and Risk Management Applied Cybersecurity Division Cybersecurity and Privacy Applications National Cybersecurity Center of Excellence (NCCoE) National Initiative for Cybersecurity Education (NICE) Contact Us Information Technology Laboratory Computer Security Resource Center Publications NIST SP 800-226 Guidelines for Evaluating Differential Privacy Guarantees Share to Facebook Share to X Share to LinkedIn Share ia Email Documentation Topics Date Published: March 2025 Author(s) Joseph Near (University of Vermont) , David Darais (Galois) , Naomi Lefkovitz (NIST) , Gary Howarth (NIST) Abstract This publication describes differential privacy — a mathematical framework that quantifies privacy loss to entities when their data appears in a dataset. The primary goal of this publication is to help practitioners of all backgrounds better understand how to think about differentially private software solutions. Multiple factors for consideration are identified in a differential privacy pyramid along with several privacy hazards, which are common pitfalls that arise as the mathematical framework of differential privacy is realized in practice. This publication describes differential privacy — a mathematical framework that quantifies privacy loss to entities when their data appears in a dataset. The primary goal of this publication is to help practitioners of all backgrounds better understand how to think about differentially private... See full abstract This publication describes differential privacy — a mathematical framework that quantifies privacy loss to entities when their data appears in a dataset. The primary goal of this publication is to help practitioners of all backgrounds better understand how to think about differentially private software solutions. Multiple factors for consideration are identified in a differential privacy pyramid along with several privacy hazards, which are common pitfalls that arise as the mathematical framework of differential privacy is realized in practice. Hide full abstract Keywords anonymization ; data analytics ; data privacy ; de-identification ; differential privacy ; privacy ; privacy-enhancing technologies Control Families None selected Documentation Publication: https://doi.org/10.6028/NIST.SP.800-226 Download URL Supplemental Material: Python Jupyter notebooks NIST news article Document History: 12/11/23: SP 800-226 (Draft) 03/06/25: SP 800-226 (Final) Topics Security and Privacy analytics , privacy Applications mathematics HEADQUARTERS 100 Bureau Drive Gaithersburg, MD 20899 X (link is external) facebook (link is external) linkedin (link is external) instagram (link is external) youtube (link is external) rss govdelivery (link is external) Want updates about CSRC and our publications? Subscribe Contact Us | Our Other Offices Send inquiries to [email protected] Site Privacy Accessibility Privacy Program Copyrights Vulnerability Disclosure No Fear Act Policy FOIA Environmental Policy Scientific Integrity Information Quality Standards Commerce.gov Science.gov USA.gov Vote.gov