Measuring the Probability of Re- Identification
The application of de-identification algorithms in practice requires the data custodian to be able to measure the probability of re-identification. Such measurement will inform the custodian whether the probability of re-identification is high or not. If the probability is high, then de-identification methods need to be applied. This means that specific metrics for the measurement of the probability of reidentification are needed, as well as guidelines for interpreting their values. In this chapter we present a set of metrics and decision rules for measuring and interpreting the probability of re-identification for identity disclosure.