Poster
in
Workshop: Synthetic Data Generation with Generative AI

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

Alexander Boudewijn ⋅ Andrea Filippo Ferraris ⋅ Daniele Panfilo ⋅ Vanessa Cocca ⋅ Sabrina Zinutti ⋅ Karel De Schepper ⋅ Carlo Chauvenet

Keywords: anonymization metrics privacy differential privacy Synthetic Data

Project Page [ OpenReview]

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.

Chat is not available.