Privacy-Preserving Generative Models: A Comprehensive Survey

TL;DR

This survey systematically categorizes privacy and utility aspects of generative models like GANs and VAEs, analyzing 100 studies to guide future research in privacy-preserving generative modeling.

Contribution

It introduces new taxonomies for privacy and utility metrics in generative models and provides a comprehensive analysis of existing research.

Findings

Developed novel taxonomies for privacy and utility metrics.

Analyzed 100 research publications on privacy-preserving generative models.

Discussed current challenges and future directions in the field.

Abstract

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.