didentification

Didentification is a term that appears in some discussions of privacy and data governance but is not a widely standardized concept in the literature. When used, it is often considered a variant or mistaken form of de-identification. In practice, didentification generally refers to efforts to prevent or reduce the ability to identify individuals within a data set, typically by removing or obscuring personal identifiers. Because the term is not consistently defined, professionals usually prefer established terms such as de-identification or anonymization to describe these practices.

Key methods associated with didentification, as described in various sources, include the removal of direct identifiers (such as names, social security numbers, and exact dates), generalization or suppression of quasi-identifiers (like age ranges or broad location data), pseudonymization (replacing identifiers with pseudonyms), data masking, and the application of privacy-preserving techniques such as differential privacy or the use of synthetic data. The goal is to reduce re-identification risk while preserving useful data for analysis.

Applications of didentification-like practices occur across domains that handle sensitive information, including healthcare, research, and public data release. Regulators and institutions emphasize that de-identification efforts must be documented, auditable, and subject to risk assessment, as re-identification remains a possible threat when data are combined with other sources.

Terminology notes: due to its nonstandard status, didentification can cause confusion with de-identification, anonymization, and related privacy techniques. When precision is important, it is advisable to use established terms and describe the specific methods and risk assessments employed.

See also: de-identification, anonymization, pseudonymization, differential privacy, data masking.