Generative Adversarial Networks: A Survey Towards Private and Secure Applications

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.

References in corpus (18)

• Conditional Generative Adversarial Nets
• Generating Videos with Scene Dynamics
• GIDS: GAN based Intrusion Detection System for In-Vehicle Network
• Generating Adversarial Malware Examples for Black-Box Attacks Based on GAN
• Real-valued (Medical) Time Series Generation with Recurrent Conditional GANs
• Adversarial Transformation Networks: Learning to Generate Adversarial Examples
• APE-GAN: Adversarial Perturbation Elimination with GAN
• Generative Models for Effective ML on Private, Decentralized Datasets
• Machine Learning Models that Remember Too Much
• FedGAN: Federated Generative Adversarial Networks for Distributed Data
• GAMIN: An Adversarial Approach to Black-Box Model Inversion
• Generalization in Generative Adversarial Networks: A Novel Perspective from Privacy Protection
• CorGAN: Correlation-Capturing Convolutional Generative Adversarial Networks for Generating Synthetic Healthcare Records
• Membership Model Inversion Attacks for Deep Networks
• Better accuracy with quantified privacy: representations learned via reconstructive adversarial network
• Improved Detection of Adversarial Images Using Deep Neural Networks
• GanDef: A GAN based Adversarial Training Defense for Neural Network Classifier
• Adversarial Privacy Preserving Graph Embedding against Inference Attack