2023/11/29 by Alexander Boudewijn, Andrea Filippo Ferraris, Daniele Panfilo +4 · 1 voice
Computer Science · Mathematics · #cs.AI #cs.CR #cs.DB #stat.ML
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.