Data Anonymity Meets Non-discrimination

We investigate the relation between t-closeness, a well-known model of data anonymization, and α-protection, a model of data discrimination. We show that t-closeness implies bd(t)-protection, for a bound function bd() depending on the discrimination measure at hand. This allows us to adapt an inference control method, the Mondrian multidimensional generalization technique, to the purpose of non-discrimination data protection. The parallel between the two analytical models raises intriguing issues on the interplay between data anonymization and non-discrimination research in data mining.