Privacy Measurements in Tabular Synthetic Data: State of the Art and Future Research Directions

Alexander Theodorus Petrus Boudewijn, Andrea Filippo Ferraris, Daniele Panfilo, Vanessa Cocca, Sabrina Zinutti, Karel De Schepper, Carlo Rossi Chauvenet

Keywords: Synthetic data, privacy, metrics, differential privacy, anonymization

TL;DR: We survey available methods for assessing the degree to which structured synthetic datasets protect real data subjects' right to privacy

Abstract:

Synthetic data (SD) have garnered attention as a privacy enhancing technology. Unfortunately, there is no standard for assessing their degree of privacy protection. In this paper, we discuss proposed assessment approaches. This contributes to the development of SD privacy standards; stimulates multi-disciplinary discussion; and helps SD researchers make informed modeling and evaluation decisions.

Submission Number: 2