Compliance
re-identification risk
Probability an individual in source data can be matched to synthetic records.
Definition
The probability or likelihood that an individual from the source dataset can be correctly linked or matched to records in the synthetic output using available linkable information or attacks. The Guide requires quantitative and qualitative re‑identification testing (membership, attribute, and record linkage tests) and threshold‑based criteria to assess and manage this risk.
Related Terms
identifiable personal data
Data that enables identification of a natural person....
privacy risk
Likelihood × impact of privacy harms....
Data risk
Risks from data quality, provenance, representativeness, and privacy....
Anonymized data
Data processed to prevent re-identification of individuals....
De-identified information
Personal data processed so an individual is not identifiable....