# GS-WGAN: A Gradient-Sanitized Approach for Learning Differentially Private Generators

arXiv: https://arxiv.org/abs/2006.08265 · HTML: https://mlsanity.com/paper/2006.08265/

## Key facts

- Cited by 117 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Jun 2020.

## Built on by (most cited first, 30 of 117)

- [Large Language Models Can Be Strong Differentially Private Learners](https://mlsanity.com/paper/2110.05679/) (2021)
- [Privacy for Free: How does Dataset Condensation Help Privacy?](https://mlsanity.com/paper/2206.00240/) (2022)
- [Machine Learning for Synthetic Data Generation: A Review](https://mlsanity.com/paper/2302.04062/) (2023)
- [Differentially Private Diffusion Models](https://mlsanity.com/paper/2210.09929/) (2022)
- [Differentially Private Diffusion Models Generate Useful Synthetic Images](https://mlsanity.com/paper/2302.13861/) (2023)
- [CTAB-GAN+: Enhancing Tabular Data Synthesis](https://mlsanity.com/paper/2204.00401/) (2022)
- [Differentially Private Language Models for Secure Data Sharing](https://mlsanity.com/paper/2210.13918/) (2022)
- [Membership Inference Attacks against Synthetic Data through Overfitting Detection](https://mlsanity.com/paper/2302.12580/) (2023)
- [Don't Generate Me: Training Differentially Private Generative Models with Sinkhorn Divergence](https://mlsanity.com/paper/2111.01177/) (2021)
- [SoK: Privacy-Preserving Data Synthesis](https://mlsanity.com/paper/2307.02106/) (2023)
- [Private Set Generation with Discriminative Information](https://mlsanity.com/paper/2211.04446/) (2022)
- [DataLens: Scalable Privacy Preserving Training via Gradient Compression and Aggregation](https://mlsanity.com/paper/2103.11109/) (2021)
- [DP-LDMs: Differentially Private Latent Diffusion Models](https://mlsanity.com/paper/2305.15759/) (2023)
- [Pre-trained Perceptual Features Improve Differentially Private Image Generation](https://mlsanity.com/paper/2205.12900/) (2022)
- [A Comprehensive Survey of Synthetic Tabular Data Generation](https://mlsanity.com/paper/2504.16506/) (2025)
- [PEARL: Data Synthesis via Private Embeddings and Adversarial Reconstruction Learning](https://mlsanity.com/paper/2106.04590/) (2021)
- [From Identifiable Causal Representations to Controllable Counterfactual Generation: A Survey on Causal Generative Modeling](https://mlsanity.com/paper/2310.11011/) (2023)
- [How Private are DP-SGD Implementations?](https://mlsanity.com/paper/2403.17673/) (2024)
- [Hermite Polynomial Features for Private Data Generation](https://mlsanity.com/paper/2106.05042/) (2021)
- [FedMed-GAN: Federated Domain Translation on Unsupervised Cross-Modality Brain Image Synthesis](https://mlsanity.com/paper/2201.08953/) (2022)
- [Perceptual Indistinguishability-Net (PI-Net): Facial Image Obfuscation with Manipulable Semantics](https://mlsanity.com/paper/2104.01753/) (2021)
- [Differentially Private Fine-Tuning of Diffusion Models](https://mlsanity.com/paper/2406.01355/) (2024)
- [Differentially Private Sliced Wasserstein Distance](https://mlsanity.com/paper/2107.01848/) (2021)
- [On the Privacy Properties of GAN-generated Samples](https://mlsanity.com/paper/2206.01349/) (2022)
- [Private GANs, Revisited](https://mlsanity.com/paper/2302.02936/) (2023)
- [Scalable DP-SGD: Shuffling vs. Poisson Subsampling](https://mlsanity.com/paper/2411.04205/) (2024)
- [Differentially Private Neural Tangent Kernels for Privacy-Preserving Data Generation](https://mlsanity.com/paper/2303.01687/) (2023)
- [Reducing bias and increasing utility by federated generative modeling of medical images using a centralized adversary](https://mlsanity.com/paper/2101.07235/) (2021)
- [DPD-fVAE: Synthetic Data Generation Using Federated Variational Autoencoders With Differentially-Private Decoder](https://mlsanity.com/paper/2211.11591/) (2022)
- [Challenges and Remedies to Privacy and Security in AIGC: Exploring the Potential of Privacy Computing, Blockchain, and Beyond](https://mlsanity.com/paper/2306.00419/) (2023)

## Abstract (arXiv)

The wide-spread availability of rich data has fueled the growth of machine learning applications in numerous domains. However, growth in domains with highly-sensitive data (e.g., medical) is largely hindered as the private nature of data prohibits it from being shared. To this end, we propose Gradient-sanitized Wasserstein Generative Adversarial Networks (GS-WGAN), which allows releasing a sanitized form of the sensitive data with rigorous privacy guarantees. In contrast to prior work, our approach is able to distort gradient information more precisely, and thereby enabling training deeper models which generate more informative samples. Moreover, our formulation naturally allows for training GANs in both centralized and federated (i.e., decentralized) data scenarios. Through extensive experiments, we find our approach consistently outperforms state-of-the-art approaches across multiple metrics (e.g., sample quality) and datasets.