ε-inclusion： privacy preserving re-publication of dynamic datasets

This paper presents a novel privacy principle, ε-inclusion, for re-publishing sensitive dynamic datasets, ε-inclusion releases all the quasi-identifier values directly and uses permutation-based method and substitution to anonymize the microdata. Combined with generalization-based methods, ε-inclusion protects privacy and captures a large amount of correlation in the microdata. We develop an effective algorithm for computing anonymized tables that obey the ε-inclusion privacy requirement. Extensive experiments confirm that our solution allows significantly more effective data analysis than generalization-based methods.