Privacy Measurements in Tabular Synthetic Data: State of the Art and Future Research Directions
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.
Cite
Text
Boudewijn et al. "Privacy Measurements in Tabular Synthetic Data: State of the Art and Future Research Directions." NeurIPS 2023 Workshops: SyntheticData4ML, 2023.Markdown
[Boudewijn et al. "Privacy Measurements in Tabular Synthetic Data: State of the Art and Future Research Directions." NeurIPS 2023 Workshops: SyntheticData4ML, 2023.](https://mlanthology.org/neuripsw/2023/boudewijn2023neuripsw-privacy/)BibTeX
@inproceedings{boudewijn2023neuripsw-privacy,
title = {{Privacy Measurements in Tabular Synthetic Data: State of the Art and Future Research Directions}},
author = {Boudewijn, Alexander Theodorus Petrus and Ferraris, Andrea Filippo and Panfilo, Daniele and Cocca, Vanessa and Zinutti, Sabrina and De Schepper, Karel and Chauvenet, Carlo Rossi},
booktitle = {NeurIPS 2023 Workshops: SyntheticData4ML},
year = {2023},
url = {https://mlanthology.org/neuripsw/2023/boudewijn2023neuripsw-privacy/}
}