On the connection between t-closeness and differential privacy for data releases

Abstract

t-Closeness was introduced as an improvement of the well-known k-anonymity privacy model for data release. On the other hand, e-differential privacy was originally proposed as a privacy property for answers to on-line database queries and it has been very welcome in academic circles. In spite of their quite diverse origins and motivations, we show in this paper that t-closeness and e-differential privacy actually provide related privacy guarantees when applied to off-line data release. Specifically, k-anonymity for the quasi-identifiers combined with differential privacy for the confidential attributes yields t-closeness in expectation.