AI engineering glossary · AI ethics law product
What is DP (differential privacy)?
Differential privacy (also called DP): A mathematical guarantee that the result of an analysis or training run barely changes whether or not any one person's data is included, usually achieved by adding calibrated random noise. A smaller privacy parameter epsilon means stronger privacy and less accurate results.
Differential privacy: an example
A phone maker collects usage statistics with noise added so the total is accurate for millions of users, yet no individual's contribution can be inferred.
Related terms
More AI ethics law product terms
- Disparate impact
- DP-SGD
- DPDP Act 2023
- DPDP Rules 2025
- Edit rate
- Equal opportunity
- Equalized odds
- Escalation rate
Where you learn it
Differential privacy is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.