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: [ Synthetic Data ] [ differential privacy ] [ privacy ] [ metrics ] [ anonymization ]
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.