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

NeurIPS 2023 Workshop on Synthetic Data Generation with Generative AI Synthetic data (SD) have garnered attention as a privacy enhancing technology. Unfortunately, there is no standard for quantifying their degree of privacy protection. In this paper, we discuss proposed quantification approaches. T...

Full description

Saved in:
Bibliographic Details
Main Authors Boudewijn, Alexander, Ferraris, Andrea Filippo, Panfilo, Daniele, Cocca, Vanessa, Zinutti, Sabrina, De Schepper, Karel, Chauvenet, Carlo Rossi
Format Journal Article
LanguageEnglish
Published 29.11.2023
Subjects
Computer Science - Artificial Intelligence
Computer Science - Cryptography and Security
Computer Science - Databases
Statistics - Machine Learning
Online AccessGet full text

Cover

More Information
Summary:NeurIPS 2023 Workshop on Synthetic Data Generation with Generative AI Synthetic data (SD) have garnered attention as a privacy enhancing technology. Unfortunately, there is no standard for quantifying their degree of privacy protection. In this paper, we discuss proposed quantification approaches. This contributes to the development of SD privacy standards; stimulates multi-disciplinary discussion; and helps SD researchers make informed modeling and evaluation decisions.
DOI:10.48550/arxiv.2311.17453