# Differentially Private Generative Adversarial Networks with Model Inversion

arXiv: https://arxiv.org/abs/2201.03139 · HTML: https://mlsanity.com/paper/2201.03139/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 27 references that are in the map.
- First posted on arXiv 10 Jan 2022.

## Builds on (most cited first, 15 of 15)

- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [Membership Inference Attacks against Machine Learning Models](https://mlsanity.com/paper/1610.05820/) (2016)
- [Improved Training of Wasserstein GANs](https://mlsanity.com/paper/1704.00028/) (2017)
- [Context Encoders: Feature Learning by Inpainting](https://mlsanity.com/paper/1604.07379/) (2016)
- [Self-Attention Generative Adversarial Networks](https://mlsanity.com/paper/1805.08318/) (2018)
- [Renyi Differential Privacy](https://mlsanity.com/paper/1702.07476/) (2017)
- [Wasserstein GAN](https://mlsanity.com/paper/1701.07875/) (2017)
- [Real-valued (Medical) Time Series Generation with Recurrent Conditional GANs](https://mlsanity.com/paper/1706.02633/) (2017)
- [Differentially Private Generative Adversarial Network](https://mlsanity.com/paper/1802.06739/) (2018)
- [Pros and Cons of GAN Evaluation Measures: New Developments](https://mlsanity.com/paper/2103.09396/) (2021)
- [DP-CGAN: Differentially Private Synthetic Data and Label Generation](https://mlsanity.com/paper/2001.09700/) (2020)
- [GS-WGAN: A Gradient-Sanitized Approach for Learning Differentially Private Generators](https://mlsanity.com/paper/2006.08265/) (2020)
- [Generative Models for Effective ML on Private, Decentralized Datasets](https://mlsanity.com/paper/1911.06679/) (2019)
- [Stabilizing GAN Training with Multiple Random Projections](https://mlsanity.com/paper/1705.07831/) (2017)

## Built on by (most cited first, 7 of 7)

- [Differentially Private Diffusion Models Generate Useful Synthetic Images](https://mlsanity.com/paper/2302.13861/) (2023)
- [PrivImage: Differentially Private Synthetic Image Generation using Diffusion Models with Semantic-Aware Pretraining](https://mlsanity.com/paper/2311.12850/) (2023)
- [From Easy to Hard: Building a Shortcut for Differentially Private Image Synthesis](https://mlsanity.com/paper/2504.01395/) (2025)
- [A Unified View of Differentially Private Deep Generative Modeling](https://mlsanity.com/paper/2309.15696/) (2023)
- [Large-Scale Public Data Improves Differentially Private Image Generation Quality](https://mlsanity.com/paper/2309.00008/) (2023)
- [DPGOMI: Differentially Private Data Publishing with Gaussian Optimized Model Inversion](https://mlsanity.com/paper/2310.04528/) (2023)
- [Differentially Private Adaptation of Diffusion Models via Noisy Aggregated Embeddings](https://mlsanity.com/paper/2411.14639/) (2024)

## 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.