Data to 7 Oct 2026

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

arXiv 2006.08265 ↗First posted 15 Jun 2020cs.LG cs.CR stat.MLcited by 117

Not on the map. Why?

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.

Key facts. Cited by 117 papers in the map (data through 7 Oct 2026). First posted on arXiv 15 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 14; 2022: 24; 2023: 31; 2024: 22; 2025: 19; 2026: 7.

117 papers.

Sort:

By area:

2021Large Language Models Can Be Strong Differentially Private Learnerscited by 405
2022Privacy for Free: How does Dataset Condensation Help Privacy?cited by 119
2022Differentially Private Diffusion Modelscited by 118
2023Machine Learning for Synthetic Data Generation: A Reviewcited by 118
2023Differentially Private Diffusion Models Generate Useful Synthetic Imagescited by 85
2022CTAB-GAN+: Enhancing Tabular Data Synthesiscited by 70
2022Differentially Private Language Models for Secure Data Sharingcited by 68
2023Membership Inference Attacks against Synthetic Data through Overfitting Detectioncited by 66
2021Don't Generate Me: Training Differentially Private Generative Models with Sinkhorn Divergencecited by 54
2023SoK: Privacy-Preserving Data Synthesiscited by 37
2022Private Set Generation with Discriminative Informationcited by 34
2021DataLens: Scalable Privacy Preserving Training via Gradient Compression and Aggregationcited by 31

38 more

2022Pre-trained Perceptual Features Improve Differentially Private Image Generationcited by 28
2023DP-LDMs: Differentially Private Latent Diffusion Modelscited by 28
2025A Comprehensive Survey of Synthetic Tabular Data Generationcited by 27
2021PEARL: Data Synthesis via Private Embeddings and Adversarial Reconstruction Learningcited by 23
2024How Private are DP-SGD Implementations?cited by 22
2021Hermite Polynomial Features for Private Data Generationcited by 21
2022FedMed-GAN: Federated Domain Translation on Unsupervised Cross-Modality Brain Image Synthesiscited by 21
2023From Identifiable Causal Representations to Controllable Counterfactual Generation: A Survey on Causal Generative Modelingcited by 21
2021Perceptual Indistinguishability-Net (PI-Net): Facial Image Obfuscation with Manipulable Semanticscited by 20
2021Differentially Private Sliced Wasserstein Distancecited by 19
2024Differentially Private Fine-Tuning of Diffusion Modelscited by 18
2023Private GANs, Revisitedcited by 17
2022On the Privacy Properties of GAN-generated Samplescited by 16
2024Scalable DP-SGD: Shuffling vs. Poisson Subsamplingcited by 16
2023Differentially Private Neural Tangent Kernels for Privacy-Preserving Data Generationcited by 15
2021Reducing bias and increasing utility by federated generative modeling of medical images using a centralized adversarycited by 14
2022DPD-fVAE: Synthetic Data Generation Using Federated Variational Autoencoders With Differentially-Private Decodercited by 14
2023Challenges and Remedies to Privacy and Security in AIGC: Exploring the Potential of Privacy Computing, Blockchain, and Beyondcited by 14
2022DP2-VAE: Differentially Private Pre-trained Variational Autoencoderscited by 13
2023DPMLBench: Holistic Evaluation of Differentially Private Machine Learningcited by 13
2025Differentially Private Synthetic Data via APIs 3: Using Simulators Instead of Foundation Modelcited by 13
2023Recent Advances of Differential Privacy in Centralized Deep Learning: A Systematic Surveycited by 12
2023PrivImage: Differentially Private Synthetic Image Generation using Diffusion Models with Semantic-Aware Pretrainingcited by 12
2025DPImageBench: A Unified Benchmark for Differentially Private Image Synthesiscited by 11
2021PATE-AAE: Incorporating Adversarial Autoencoder into Private Aggregation of Teacher Ensembles for Spoken Command Classificationcited by 10
2022Noise-Aware Statistical Inference with Differentially Private Synthetic Datacited by 9
2023PPGenCDR: A Stable and Robust Framework for Privacy-Preserving Cross-Domain Recommendationcited by 9
2021On Utility and Privacy in Synthetic Genomic Datacited by 8
2022On the Utility Recovery Incapability of Neural Net-based Differential Private Tabular Training Data Synthesizer under Privacy Deregulationcited by 8
2021DTGAN: Differential Private Training for Tabular GANscited by 7
2022Differentially Private Generative Adversarial Networks with Model Inversioncited by 7
2023Deep Generative Models, Synthetic Tabular Data, and Differential Privacy: An Overview and Synthesiscited by 7
2023ODIM: Outlier Detection via Likelihood of Under-Fitted Generative Modelscited by 6
2023Federated Learning via Input-Output Collaborative Distillationcited by 6
2025From Easy to Hard: Building a Shortcut for Differentially Private Image Synthesiscited by 6
2021Federated CycleGAN for Privacy-Preserving Image-to-Image Translationcited by 5
2024DP-TLDM: Differentially Private Tabular Latent Diffusion Modelcited by 5
2024State-of-the-Art Approaches to Enhancing Privacy Preservation of Machine Learning Datasets: A Surveycited by 5

50 most cited of 117 All 117 (JSON)