Metrics for Privacy-Preserving Generative Models: A Comprehensive Survey
ACM Computing Surveys · 31.10.2026 · 58 (13) · 1-35
DOI: 10.1145/3815777 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Computing Surveys, online erschienen am 23.06.2026. Verfasst von Debalina Padariya und 3 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 139 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Alan Turing Institute under the Turing/Accenture.
Abstract (Originalsprache)
Generative models are extremely widely used, both in research and practice. Although many studies have shown privacy threats against generative models or proposed privacy protections, there is no systematic survey on which metrics should be used to quantify privacy and utility of generative models. In this article, we therefore present new taxonomies for privacy and utility metrics for generative models, including taxonomies for attacks against generative models and a discussion of the most common approaches for privacy protection. We also propose guidelines for selecting appropriate metrics in specific scenarios and show commonly used metrics in several use cases. Finally, we discuss open challenges and promising future research directions.
Förderung
- Alan Turing Institute under the Turing/Accenture
Zitieren
APA
Padariya, D., Wagner, I., Taherkhani, A., & Boiten, E. A. (2026). Metrics for Privacy-Preserving Generative Models: A Comprehensive Survey. ACM Computing Surveys, 58(13), 1-35. https://doi.org/10.1145/3815777
Vancouver
Padariya D, Wagner I, Taherkhani A, Boiten EA. Metrics for Privacy-Preserving Generative Models: A Comprehensive Survey. ACM Computing Surveys. 2026;58(13):1-35. doi:10.1145/3815777
BibTeX
@article{Padariya2026,
author = {Padariya, Debalina and Wagner, Isabel and Taherkhani, Aboozar and Boiten, Eerke A.},
title = {Metrics for Privacy-Preserving Generative Models: A Comprehensive Survey},
journal = {ACM Computing Surveys},
year = {2026},
volume = {58},
number = {13},
pages = {1--35},
doi = {10.1145/3815777}
}
EUVIMED