Saved in:
Bibliographic Details
Main Authors: Padariya, Debalina, Wagner, Isabel, Taherkhani, Aboozar, Boiten, Eerke
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2502.03668
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916600243814400
author Padariya, Debalina
Wagner, Isabel
Taherkhani, Aboozar
Boiten, Eerke
author_facet Padariya, Debalina
Wagner, Isabel
Taherkhani, Aboozar
Boiten, Eerke
contents Despite the generative model's groundbreaking success, the need to study its implications for privacy and utility becomes more urgent. Although many studies have demonstrated the privacy threats brought by GANs, no existing survey has systematically categorized the privacy and utility perspectives of GANs and VAEs. In this article, we comprehensively study privacy-preserving generative models, articulating the novel taxonomies for both privacy and utility metrics by analyzing 100 research publications. Finally, we discuss the current challenges and future research directions that help new researchers gain insight into the underlying concepts.
format Preprint
id arxiv_https___arxiv_org_abs_2502_03668
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Privacy-Preserving Generative Models: A Comprehensive Survey
Padariya, Debalina
Wagner, Isabel
Taherkhani, Aboozar
Boiten, Eerke
Machine Learning
Cryptography and Security
Despite the generative model's groundbreaking success, the need to study its implications for privacy and utility becomes more urgent. Although many studies have demonstrated the privacy threats brought by GANs, no existing survey has systematically categorized the privacy and utility perspectives of GANs and VAEs. In this article, we comprehensively study privacy-preserving generative models, articulating the novel taxonomies for both privacy and utility metrics by analyzing 100 research publications. Finally, we discuss the current challenges and future research directions that help new researchers gain insight into the underlying concepts.
title Privacy-Preserving Generative Models: A Comprehensive Survey
topic Machine Learning
Cryptography and Security
url https://arxiv.org/abs/2502.03668