Generative Adversarial Networks: A Survey Towards Private and Secure Applications

TL;DR

This survey reviews the current state of Generative Adversarial Networks (GAN) in privacy and security, analyzing existing methods, their strengths and weaknesses, and exploring future research directions in this emerging field.

Contribution

It provides the first comprehensive classification and analysis of GAN-based privacy and security applications, highlighting challenges and potential future research avenues.

Findings

Classified existing GAN privacy/security works into categories

Analyzed advantages and drawbacks of current methods

Identified key challenges and future directions

Abstract

Generative Adversarial Networks (GAN) have promoted a variety of applications in computer vision, natural language processing, etc. due to its generative model's compelling ability to generate realistic examples plausibly drawn from an existing distribution of samples. GAN not only provides impressive performance on data generation-based tasks but also stimulates fertilization for privacy and security oriented research because of its game theoretic optimization strategy. Unfortunately, there are no comprehensive surveys on GAN in privacy and security, which motivates this survey paper to summarize those state-of-the-art works systematically. The existing works are classified into proper categories based on privacy and security functions, and this survey paper conducts a comprehensive analysis of their advantages and drawbacks. Considering that GAN in privacy and security is still at a very initial stage and has imposed unique challenges that are yet to be well addressed, this paper also sheds light on some potential privacy and security applications with GAN and elaborates on some future research directions.