mlsanityData to 7 Oct 2026

Differentially Private Generative Adversarial Networks with Model Inversion

arXiv 2201.03139 ↗First posted 10 Jan 2022cs.LG cs.CRcited by 7

Not on the map. Why?

Abstract (arXiv)

To protect sensitive data in training a Generative Adversarial Network (GAN), the standard approach is to use differentially private (DP) stochastic gradient descent method in which controlled noise is added to the gradients. The quality of the output synthetic samples can be adversely affected and the training of the network may not even converge in the presence of these noises. We propose Differentially Private Model Inversion (DPMI) method where the private data is first mapped to the latent space via a public generator, followed by a lower-dimensional DP-GAN with better convergent properties. Experimental results on standard datasets CIFAR10 and SVHN as well as on a facial landmark dataset for Autism screening show that our approach outperforms the standard DP-GAN method based on Inception Score, Fr'echet Inception Distance, and classification accuracy under the same privacy guarantee.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 15 of its 27 references that are in the map. First posted on arXiv 10 Jan 2022.

Builds on

15 of 27 references.

References · 15

  1. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  2. 2016Deep Learning with Differential Privacycited by 2,682
  3. 2017Improved Training of Wasserstein GANscited by 2,223
  4. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  5. 2016Context Encoders: Feature Learning by Inpaintingcited by 1,424
  6. 2018Self-Attention Generative Adversarial Networkscited by 809
  7. 2017Renyi Differential Privacycited by 643
  8. 2017Wasserstein GANcited by 635
  9. 2017Real-valued (Medical) Time Series Generation with Recurrent Conditional GANscited by 329
  10. 2018Differentially Private Generative Adversarial Networkcited by 235
  11. 2021Pros and Cons of GAN Evaluation Measures: New Developmentscited by 121
  12. 2020DP-CGAN: Differentially Private Synthetic Data and Label Generationcited by 118
3 more
  1. 2020GS-WGAN: A Gradient-Sanitized Approach for Learning Differentially Private Generatorscited by 117
  2. 2019Generative Models for Effective ML on Private, Decentralized Datasetscited by 85
  3. 2017Stabilizing GAN Training with Multiple Random Projectionscited by 15

Built on by

Cited by year

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

7 papers.

  1. 2023Differentially Private Diffusion Models Generate Useful Synthetic Imagescited by 85
  2. 2023PrivImage: Differentially Private Synthetic Image Generation using Diffusion Models with Semantic-Aware Pretrainingcited by 12
  3. 2025From Easy to Hard: Building a Shortcut for Differentially Private Image Synthesiscited by 6
  4. 2023A Unified View of Differentially Private Deep Generative Modelingcited by 4
  5. 2023Large-Scale Public Data Improves Differentially Private Image Generation Qualitycited by 0
  6. 2023DPGOMI: Differentially Private Data Publishing with Gaussian Optimized Model Inversioncited by 0
  7. 2024Differentially Private Adaptation of Diffusion Models via Noisy Aggregated Embeddingscited by 0