| definition |
Techniques designed to make the risk of identifying a particular individual in a dataset
negligible, whilst retaining the re-usability of the dataset. The purpose is to protect
the privacy of the individual and comply with legislation, whilst enabling data sharing.
Methods include removing direct and indirect identifiers such as names, addresses,
social insurance numbers, or dates of birth, or using obfuscation methods such as
encryption, hashing, generalisation, pseudonymisation, and perturbation.
|
|