Generative Adversarial Networks: A Survey Towards Private and Secure Applications
arXiv:2106.03785
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 (57)
- Conditional Generative Adversarial Nets
- Self-Attention Generative Adversarial Networks
- Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
- Conditional Image Synthesis With Auxiliary Classifier GANs
- Progressive Growing of GANs for Improved Quality, Stability, and Variation
- Improved Training of Wasserstein GANs
- InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets
- Generating Videos with Scene Dynamics
- BEGAN: Boundary Equilibrium Generative Adversarial Networks
- Pose Guided Person Image Generation
- Data Synthesis based on Generative Adversarial Networks
- GIDS: GAN based Intrusion Detection System for In-Vehicle Network
- Generating Natural Adversarial Examples
- cGANs with Projection Discriminator
- How Generative Adversarial Networks and Their Variants Work: An Overview
- Generating Adversarial Malware Examples for Black-Box Attacks Based on GAN
- Generating Multi-label Discrete Patient Records using Generative Adversarial Networks
- MaskGAN: Better Text Generation via Filling in the______
- Differentially Private Generative Adversarial Network
- Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Models
- Real-valued (Medical) Time Series Generation with Recurrent Conditional GANs
- Generating Adversarial Examples with Adversarial Networks
- Good Semi-supervised Learning that Requires a Bad GAN
- Adversarial Transformation Networks: Learning to Generate Adversarial Examples
- Deep Models Under the GAN: Information Leakage from Collaborative Deep Learning
- MD-GAN: Multi-Discriminator Generative Adversarial Networks for Distributed Datasets
- PrivacyNet: Semi-Adversarial Networks for Multi-attribute Face Privacy
- Constructing Unrestricted Adversarial Examples with Generative Models
- Texture Synthesis with Spatial Generative Adversarial Networks
- EEG-GAN: Generative adversarial networks for electroencephalograhic (EEG) brain signals
- Generative Adversarial Trainer: Defense to Adversarial Perturbations with GAN
- PPGAN: Privacy-preserving Generative Adversarial Network
- Unsupervised Learning of Visual Structure using Predictive Generative Networks
- APE-GAN: Adversarial Perturbation Elimination with GAN
- Privacy-Preserving Human Activity Recognition from Extreme Low Resolution
- AutoGAN-based Dimension Reduction for Privacy Preservation
- Generative Models for Effective ML on Private, Decentralized Datasets
- Adversarial Deep Structural Networks for Mammographic Mass Segmentation
- Machine Learning Models that Remember Too Much
- FedGAN: Federated Generative Adversarial Networks for Distributed Data
- Quick and Easy Time Series Generation with Established Image-based GANs
- GAMIN: An Adversarial Approach to Black-Box Model Inversion
- Decentralized Learning of Generative Adversarial Networks from Non-iid Data
- Generalization in Generative Adversarial Networks: A Novel Perspective from Privacy Protection
- Machine Learning with Membership Privacy using Adversarial Regularization
- Towards Robust and Privacy-preserving Text Representations
- CorGAN: Correlation-Capturing Convolutional Generative Adversarial Networks for Generating Synthetic Healthcare Records
- Emotionless: Privacy-Preserving Speech Analysis for Voice Assistants
- Intriguing properties of adversarial training at scale
- Membership Model Inversion Attacks for Deep Networks
- Better accuracy with quantified privacy: representations learned via reconstructive adversarial network
- Understanding Compressive Adversarial Privacy
- DeepMasterPrints: Generating MasterPrints for Dictionary Attacks via Latent Variable Evolution
- Application-driven Privacy-preserving Data Publishing with Correlated Attributes
- 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