mlsanityData to 7 Oct 2026

Generative Adversarial Networks: A Survey Towards Private and Secure Applications

arXiv 2106.03785 ↗First posted 7 Jun 2021cs.LG cs.CRcited by 15

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). Builds on 92 of its 162 references that are in the map. First posted on arXiv 7 Jun 2021.

Builds on

92 of 162 references.

References · 92

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  3. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  4. 2016Deep Learning with Differential Privacycited by 2,682
  5. 2017Improved Training of Wasserstein GANscited by 2,223
  6. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  7. 2014Conditional Generative Adversarial Netscited by 2,152
  8. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  9. 2016Least Squares Generative Adversarial Networkscited by 1,000
  10. 2016Practical Black-Box Attacks against Machine Learningcited by 893
  11. 2016InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Netscited by 858
  12. 2018Self-Attention Generative Adversarial Networkscited by 809
38 more
  1. 2016Conditional Image Synthesis With Auxiliary Classifier GANscited by 562
  2. 2016Generating Videos with Scene Dynamicscited by 376
  3. 2018Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Modelscited by 362
  4. 2017Real-valued (Medical) Time Series Generation with Recurrent Conditional GANscited by 329
  5. 2017Deep Models Under the GAN: Information Leakage from Collaborative Deep Learningcited by 326
  6. 2018Generating Adversarial Examples with Adversarial Networkscited by 256
  7. 2018cGANs with Projection Discriminatorcited by 253
  8. 2017Pose Guided Person Image Generationcited by 251
  9. 2018Beyond Inferring Class Representatives: User-Level Privacy Leakage From Federated Learningcited by 242
  10. 2019The Secret Revealer: Generative Model-Inversion Attacks Against Deep Neural Networkscited by 241
  11. 2018Differentially Private Generative Adversarial Networkcited by 235
  12. 2015The Variational Fair Autoencodercited by 223
  13. 2017Generating Multi-label Discrete Patient Records using Generative Adversarial Networkscited by 197
  14. 2018Data Synthesis based on Generative Adversarial Networkscited by 184
  15. 2017Generating Natural Adversarial Examplescited by 182
  16. 2018Machine Learning with Membership Privacy using Adversarial Regularizationcited by 177
  17. 2017Machine Learning Models that Remember Too Muchcited by 165
  18. 2018Constructing Unrestricted Adversarial Examples with Generative Modelscited by 135
  19. 2013Hacking Smart Machines with Smarter Ones: How to Extract Meaningful Data from Machine Learning Classifierscited by 128
  20. 2017BEGAN: Boundary Equilibrium Generative Adversarial Networkscited by 121
  21. 2016High-Resolution Image Inpainting using Multi-Scale Neural Patch Synthesiscited by 89
  22. 2018MaskGAN: Better Text Generation via Filling in the______cited by 89
  23. 2020FedGAN: Federated Generative Adversarial Networks for Distributed Datacited by 89
  24. 2017Good Semi-supervised Learning that Requires a Bad GANcited by 85
  25. 2019Generative Models for Effective ML on Private, Decentralized Datasetscited by 85
  26. 2018Privacy Preserving Machine Learning: Threats and Solutionscited by 78
  27. 2018Towards Robust and Privacy-preserving Text Representationscited by 75
  28. 2017Generating Adversarial Malware Examples for Black-Box Attacks Based on GANcited by 74
  29. 2016Semantic Segmentation using Adversarial Networkscited by 73
  30. 2018Learning to Anonymize Faces for Privacy Preserving Action Detectioncited by 63
  31. 2017Adversarial Transformation Networks: Learning to Generate Adversarial Examplescited by 60
  32. 2019Federated Learning with Bayesian Differential Privacycited by 60
  33. 2019AdvFaces: Adversarial Face Synthesiscited by 59
  34. 2017Adversarial examples for generative modelscited by 58
  35. 2017APE-GAN: Adversarial Perturbation Elimination with GANcited by 57
  36. 2020LSTM-TrajGAN: A Deep Learning Approach to Trajectory Privacy Protectioncited by 57
  37. 2018MD-GAN: Multi-Discriminator Generative Adversarial Networks for Distributed Datasetscited by 49
  38. 2018EEG-GAN: Generative adversarial networks for electroencephalograhic (EEG) brain signalscited by 46

50 most cited of 92 All 92 (JSON)

Built on by

Cited by year

Citing papers per year: 2022: 5; 2023: 5; 2024: 4; 2025: 1.

15 papers.

Sort:

  1. 2023SoK: Privacy-Preserving Data Synthesiscited by 37
  2. 2022Anonymizing Speech with Generative Adversarial Networks to Preserve Speaker Privacycited by 20
  3. 2024Manipulating Recommender Systems: A Survey of Poisoning Attacks and Countermeasurescited by 14
  4. 2022A Review of Speech-centric Trustworthy Machine Learning: Privacy, Safety, and Fairnesscited by 13
  5. 2022Autonomy and Intelligence in the Computing Continuum: Challenges, Enablers, and Future Directions for Orchestrationcited by 12
  6. 2023DisguisOR: Holistic Face Anonymization for the Operating Roomcited by 9
  7. 2023Evading Forensic Classifiers with Attribute-Conditioned Adversarial Facescited by 6
  8. 2024Synthetic Data: Revisiting the Privacy-Utility Trade-offcited by 6
  9. 2023Adversarial Attacks and Defenses in Machine Learning-Powered Networks: A Contemporary Surveycited by 5
  10. 2023Accurate Detection of Paroxysmal Atrial Fibrillation with Certified-GAN and Neural Architecture Searchcited by 1
  11. 2024Privacy Re-identification Attacks on Tabular GANscited by 1
  12. 2025Digital Shielding for Cross-Domain Wi-Fi Signal Adaptation using Relativistic Average Generative Adversarial Networkcited by 1
3 more
  1. 2022Behavior Recognition Based on the Integration of Multigranular Motion Featurescited by 0
  2. 2022Deep Fake Detection, Deterrence and Response: Challenges and Opportunitiescited by 0
  3. 2024A Tiered GAN Approach for Monet-Style Image Generationcited by 0