Differential privacy
AIGP glossary · Last reviewed: · By Victor Humenhuk (AIGP certified)
Differential privacy - PET that blurs information within datasets so data stays meaningful but individuals can't be identified.
In the AIGP body of knowledge, Differential privacy comes up under Module 5: Existing Laws & AI · BoK III.A; Module 6: Governing AI Development · BoK III.B.
Differential privacy in context
- The scraping problem and three privacy-enhancing technologies - differential privacy, homomorphic encryption and secure multi-party computation - shape AI data strategy. (Anonymisation, Pseudonymisation and PETs)
- Master the two PETs - ==differential privacy blurs the data==; ==federated learning moves the training, not the data==. (Wrangling the Data)
Where Differential privacy is covered in the AIGP study notes
Related terms
- Anonymisation
- Pseudonymisation
- Scraping problem
- Homomorphic encryption
- Secure multi-party computation
- Data cleansing
- Data labelling
- Purpose specification & minimisation
- Federated learning
Test yourself on Differential privacy
Recognising a definition is not the same as applying it in an exam scenario. Work through the free AIGP practice questions, or read the full AIGP study guide - every study note is free.