Anatomy: simple and effective privacy preservation

TLDR

The authors introduce anatomy, a novel data publishing technique that releases quasi‑identifiers and sensitive values in separate tables while providing an efficient linear‑time algorithm to satisfy l‑diversity and minimize reconstruction error. Anatomy achieves privacy by grouping records and releasing two tables—one of quasi‑identifiers and one of sensitive values—using a linear‑time algorithm that preserves l‑diversity and captures microdata correlations. Experiments show anatomy enables aggregate analysis with average error below 10%, markedly outperforming conventional generalization methods.

Abstract

This paper presents a novel technique, anatomy, for publishing sensitive data. Anatomy releases all the quasi-identifier and sensitive values directly in two separate tables. Combined with a grouping mechanism, this approach protects privacy, and captures a large amount of correlation in the microdata. We develop a linear-time algorithm for computing anatomized tables that obey the l-diversity privacy requirement, and minimize the error of reconstructing the microdata. Extensive experiments confirm that our technique allows significantly more effective data analysis than the conventional publication method based on generalization. Specifically, anatomy permits aggregate reasoning with average error below 10%, which is lower than the error obtained from a generalized table by orders of magnitude.