# PPGAN: Privacy-preserving Generative Adversarial Network

arXiv: https://arxiv.org/abs/1910.02007 · HTML: https://mlsanity.com/paper/1910.02007/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Oct 2019.

## Built on by (most cited first, 30 of 34)

- [Machine Learning for Synthetic Data Generation: A Review](https://mlsanity.com/paper/2302.04062/) (2023)
- [DENSE: Data-Free One-Shot Federated Learning](https://mlsanity.com/paper/2112.12371/) (2021)
- [Differentially Private Diffusion Models Generate Useful Synthetic Images](https://mlsanity.com/paper/2302.13861/) (2023)
- [Threats, Attacks, and Defenses in Machine Unlearning: A Survey](https://mlsanity.com/paper/2403.13682/) (2024)
- [SoK: Privacy-Preserving Data Synthesis](https://mlsanity.com/paper/2307.02106/) (2023)
- [Elijah: Eliminating Backdoors Injected in Diffusion Models via Distribution Shift](https://mlsanity.com/paper/2312.00050/) (2023)
- [Copyright in Generative Deep Learning](https://mlsanity.com/paper/2105.09266/) (2021)
- [Enhancing One-Shot Federated Learning Through Data and Ensemble Co-Boosting](https://mlsanity.com/paper/2402.15070/) (2024)
- [DreamArtist++: Controllable One-Shot Text-to-Image Generation via Positive-Negative Adapter](https://mlsanity.com/paper/2211.11337/) (2022)
- [FedDPGAN: Federated Differentially Private Generative Adversarial Networks Framework for the Detection of COVID-19 Pneumonia](https://mlsanity.com/paper/2104.12581/) (2021)
- [Generative Adversarial Networks: A Survey Towards Private and Secure Applications](https://mlsanity.com/paper/2106.03785/) (2021)
- [DPD-fVAE: Synthetic Data Generation Using Federated Variational Autoencoders With Differentially-Private Decoder](https://mlsanity.com/paper/2211.11591/) (2022)
- [Ten Years of Generative Adversarial Nets (GANs): A survey of the state-of-the-art](https://mlsanity.com/paper/2308.16316/) (2023)
- [PrivImage: Differentially Private Synthetic Image Generation using Diffusion Models with Semantic-Aware Pretraining](https://mlsanity.com/paper/2311.12850/) (2023)
- [Recent Advances of Differential Privacy in Centralized Deep Learning: A Systematic Survey](https://mlsanity.com/paper/2309.16398/) (2023)
- [Time-series Transformer Generative Adversarial Networks](https://mlsanity.com/paper/2205.11164/) (2022)
- [From Easy to Hard: Building a Shortcut for Differentially Private Image Synthesis](https://mlsanity.com/paper/2504.01395/) (2025)
- [Generating Synthetic Health Sensor Data for Privacy-Preserving Wearable Stress Detection](https://mlsanity.com/paper/2401.13327/) (2024)
- [Exactly Minimax-Optimal Locally Differentially Private Sampling](https://mlsanity.com/paper/2410.22699/) (2024)
- [Federated Split GANs](https://mlsanity.com/paper/2207.01750/) (2022)
- [Mask Conditional Synthetic Satellite Imagery](https://mlsanity.com/paper/2302.04305/) (2023)
- [Protect and Extend -- Using GANs for Synthetic Data Generation of Time-Series Medical Records](https://mlsanity.com/paper/2402.14042/) (2024)
- [Causally Constrained Data Synthesis for Private Data Release](https://mlsanity.com/paper/2105.13144/) (2021)
- [Adversarial Robustness in Unsupervised Machine Learning: A Systematic Review](https://mlsanity.com/paper/2306.00687/) (2023)
- [Locally Optimal Private Sampling: Beyond the Global Minimax](https://mlsanity.com/paper/2510.09485/) (2025)
- [Generative Models with Information-Theoretic Protection Against Membership Inference Attacks](https://mlsanity.com/paper/2206.00071/) (2022)
- [On the causality-preservation capabilities of generative modelling](https://mlsanity.com/paper/2301.01109/) (2023)
- [Methods for generating and evaluating synthetic longitudinal patient data: a systematic review](https://mlsanity.com/paper/2309.12380/) (2023)
- [SoK: Memorisation in machine learning](https://mlsanity.com/paper/2311.03075/) (2023)
- [Harnessing Federated Generative Learning for Green and Sustainable Internet of Things](https://mlsanity.com/paper/2407.05915/) (2024)

## Abstract (arXiv)

Generative Adversarial Network (GAN) and its variants serve as a perfect representation of the data generation model, providing researchers with a large amount of high-quality generated data. They illustrate a promising direction for research with limited data availability. When GAN learns the semantic-rich data distribution from a dataset, the density of the generated distribution tends to concentrate on the training data. Due to the gradient parameters of the deep neural network contain the data distribution of the training samples, they can easily remember the training samples. When GAN is applied to private or sensitive data, for instance, patient medical records, as private information may be leakage. To address this issue, we propose a Privacy-preserving Generative Adversarial Network (PPGAN) model, in which we achieve differential privacy in GANs by adding well-designed noise to the gradient during the model learning procedure. Besides, we introduced the Moments Accountant strategy in the PPGAN training process to improve the stability and compatibility of the model by controlling privacy loss. We also give a mathematical proof of the differential privacy discriminator. Through extensive case studies of the benchmark datasets, we demonstrate that PPGAN can generate high-quality synthetic data while retaining the required data available under a reasonable privacy budget.