anonymised

Anonymised is the British English form of the adjective and past participle of anonymise, used to describe information from which personal identifiers have been removed. An anonymised dataset is intended to prevent the identification of individuals, making it suitable for sharing in research, statistics, and public reporting.

Anonymisation is distinct from pseudonymisation. In anonymisation, direct identifiers and other information that could reasonably reveal identity are removed or generalized so that re-identification is difficult or considered unlikely. Pseudonymised data replace identifiers with substitutes, but the link to the original identities can be restored with additional information, so such data remain within some data protection frameworks.

Techniques used to create anonymised data include removing or masking direct identifiers (names, addresses, social security numbers), generalising or suppressing data, data masking, hashing, perturbation, and aggregation. More formal approaches in privacy research include k-anonymity, l-diversity, and differential privacy, which aim to limit re-identification risk when datasets are combined with external information.

Applications of anonymised data include medical and health research where individual privacy must be protected, government and statistical releases, and business analytics where sharing insights does not reveal personal details. However, anonymisation has limitations: there is always some risk of re-identification through data linkage or external data sources, especially with highly detailed or large datasets. Effective anonymisation therefore requires careful governance, risk assessment, and, in some cases, ongoing auditing.

Etymology and usage notes: anonymise yields the adjective anonymised; corresponding American forms are anonymize and anonymized. The term is common in privacy, data protection, and research contexts.