mlsanityData to 7 Oct 2026

Differentially Private Generative Adversarial Network

arXiv 1802.06739 ↗First posted 19 Feb 2018cs.LG cs.CR stat.MLcited by 235

Not on the map. Why?

Abstract (arXiv)

Generative Adversarial Network (GAN) and its variants have recently attracted intensive research interests due to their elegant theoretical foundation and excellent empirical performance as generative models. These tools provide a promising direction in the studies where data availability is limited. One common issue in GANs is that the density of the learned generative distribution could concentrate on the training data points, meaning that they can easily remember training samples due to the high model complexity of deep networks. This becomes a major concern when GANs are applied to private or sensitive data such as patient medical records, and the concentration of distribution may divulge critical patient information. To address this issue, in this paper we propose a differentially private GAN (DPGAN) model, in which we achieve differential privacy in GANs by adding carefully designed noise to gradients during the learning procedure. We provide rigorous proof for the privacy guarantee, as well as comprehensive empirical evidence to support our analysis, where we demonstrate that our method can generate high quality data points at a reasonable privacy level.

Key facts. Cited by 235 papers in the map (data through 7 Oct 2026). First posted on arXiv 19 Feb 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 34; 2022: 49; 2023: 57; 2024: 48; 2025: 30; 2026: 17.

235 papers.

Sort:

By area:

  1. 2021Membership Inference Attacks on Machine Learning: A Surveycited by 306
  2. 2021How Faithful is your Synthetic Data? Sample-level Metrics for Evaluating and Auditing Generative Modelscited by 193
  3. 2023How to DP-fy ML: A Practical Guide to Machine Learning with Differential Privacycited by 150
  4. 2022Privacy for Free: How does Dataset Condensation Help Privacy?cited by 119
  5. 2022Differentially Private Diffusion Modelscited by 118
  6. 2023Machine Learning for Synthetic Data Generation: A Reviewcited by 118
  7. 2021DECAF: Generating Fair Synthetic Data Using Causally-Aware Generative Networkscited by 109
  8. 2022Synthetic Text Generation with Differential Privacy: A Simple and Practical Recipecited by 108
  9. 2023Differentially Private Diffusion Models Generate Useful Synthetic Imagescited by 85
  10. 2022Synthesizing Informative Training Samples with GANcited by 77
  11. 2022CTAB-GAN+: Enhancing Tabular Data Synthesiscited by 70
  12. 2022Differentially Private Language Models for Secure Data Sharingcited by 68
38 more
  1. 2022Synthetic Data -- what, why and how?cited by 66
  2. 2023Harnessing large-language models to generate private synthetic textcited by 65
  3. 2021Iterative Methods for Private Synthetic Data: Unifying Framework and New Methodscited by 58
  4. 2021Privacy-Preserving Machine Learning: Methods, Challenges and Directionscited by 58
  5. 2021Don't Generate Me: Training Differentially Private Generative Models with Sinkhorn Divergencecited by 54
  6. 2024Towards Memorization-Free Diffusion Modelscited by 49
  7. 2021Robin Hood and Matthew Effects: Differential Privacy Has Disparate Impact on Synthetic Datacited by 48
  8. 2021Survey: Leakage and Privacy at Inference Timecited by 44
  9. 2022A Multifaceted Benchmarking of Synthetic Electronic Health Record Generation Modelscited by 43
  10. 2022Turning the Tables: Biased, Imbalanced, Dynamic Tabular Datasets for ML Evaluationcited by 39
  11. 2023SoK: Privacy-Preserving Data Synthesiscited by 37
  12. 2022Private Synthetic Data for Multitask Learning and Marginal Queriescited by 35
  13. 2022Private Set Generation with Discriminative Informationcited by 34
  14. 2021ADePT: Auto-encoder based Differentially Private Text Transformationcited by 31
  15. 2021DataLens: Scalable Privacy Preserving Training via Gradient Compression and Aggregationcited by 31
  16. 2024How Realistic Is Your Synthetic Data? Constraining Deep Generative Models for Tabular Datacited by 29
  17. 2022Pre-trained Perceptual Features Improve Differentially Private Image Generationcited by 28
  18. 2023DP-LDMs: Differentially Private Latent Diffusion Modelscited by 28
  19. 2021An Efficient DP-SGD Mechanism for Large Scale NLP Modelscited by 27
  20. 2025A Comprehensive Survey of Synthetic Tabular Data Generationcited by 27
  21. 2022Federated Learning with GAN-based Data Synthesis for Non-IID Clientscited by 25
  22. 2021PEARL: Data Synthesis via Private Embeddings and Adversarial Reconstruction Learningcited by 23
  23. 2022Differentially Private SGDA for Minimax Problemscited by 23
  24. 2021FedDPGAN: Federated Differentially Private Generative Adversarial Networks Framework for the Detection of COVID-19 Pneumoniacited by 22
  25. 2022Bring Your Own Algorithm for Optimal Differentially Private Stochastic Minimax Optimizationcited by 22
  26. 2021Hermite Polynomial Features for Private Data Generationcited by 21
  27. 2023A Survey of What to Share in Federated Learning: Perspectives on Model Utility, Privacy Leakage, and Communication Efficiencycited by 21
  28. 2023From Identifiable Causal Representations to Controllable Counterfactual Generation: A Survey on Causal Generative Modelingcited by 21
  29. 2021Generative adversarial networks in time series: A survey and taxonomycited by 20
  30. 2021DPNAS: Neural Architecture Search for Deep Learning with Differential Privacycited by 20
  31. 2021Differentially Private Sliced Wasserstein Distancecited by 19
  32. 2025The Sum Leaks More Than Its Parts: Compositional Privacy Risks and Mitigations in Multi-Agent Collaborationcited by 19
  33. 2023Generating Private Synthetic Data with Genetic Algorithmscited by 18
  34. 2024Differentially Private Fine-Tuning of Diffusion Modelscited by 18
  35. 2023Private GANs, Revisitedcited by 17
  36. 2023TSGM: A Flexible Framework for Generative Modeling of Synthetic Time Seriescited by 16
  37. 2024Differentially Private Tabular Data Synthesis using Large Language Modelscited by 16
  38. 2021Generative Adversarial Networks: A Survey Towards Private and Secure Applicationscited by 15

50 most cited of 235 All 235 (JSON)