# Generalization in Generative Adversarial Networks: A Novel Perspective from Privacy Protection

arXiv: https://arxiv.org/abs/1908.07882 · HTML: https://mlsanity.com/paper/1908.07882/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Aug 2019.

## Built on by (most cited first, 19 of 19)

- [Membership Inference Attacks on Machine Learning: A Survey](https://mlsanity.com/paper/2103.07853/) (2021)
- [M^4I: Multi-modal Models Membership Inference](https://mlsanity.com/paper/2209.06997/) (2022)
- [Copyright in Generative Deep Learning](https://mlsanity.com/paper/2105.09266/) (2021)
- [On the Privacy Properties of GAN-generated Samples](https://mlsanity.com/paper/2206.01349/) (2022)
- [What is a Good Metric to Study Generalization of Minimax Learners?](https://mlsanity.com/paper/2206.04502/) (2022)
- [Generative Adversarial Networks: A Survey Towards Private and Secure Applications](https://mlsanity.com/paper/2106.03785/) (2021)
- [Generative Convolution Layer for Image Generation](https://mlsanity.com/paper/2111.15171/) (2021)
- [Stability and Generalization in Free Adversarial Training](https://mlsanity.com/paper/2404.08980/) (2024)
- [A Novel Generator with Auxiliary Branch for Improving GAN Performance](https://mlsanity.com/paper/2112.14968/) (2021)
- [Causally Constrained Data Synthesis for Private Data Release](https://mlsanity.com/paper/2105.13144/) (2021)
- [Dual-Model Defense: Safeguarding Diffusion Models from Membership Inference Attacks through Disjoint Data Splitting](https://mlsanity.com/paper/2410.16657/) (2024)
- [Generalization of GANs and overparameterized models under Lipschitz continuity](https://mlsanity.com/paper/2104.02388/) (2021)
- [Preserving Privacy in GANs Against Membership Inference Attack](https://mlsanity.com/paper/2311.03172/) (2023)
- [Generalization Bounds for Stochastic Gradient Langevin Dynamics: A Unified View via Information Leakage Analysis](https://mlsanity.com/paper/2112.08439/) (2021)
- [SoK: Memorisation in machine learning](https://mlsanity.com/paper/2311.03075/) (2023)
- [Rethinking Image Skip Connections in StyleGAN2](https://mlsanity.com/paper/2407.05527/) (2024)
- [Improving the expressiveness of neural vocoding with non-affine Normalizing Flows](https://mlsanity.com/paper/2106.08649/) (2021)
- [Effective Shortcut Technique for GAN](https://mlsanity.com/paper/2201.11351/) (2022)
- [Improving GANs with a Feature Cycling Generator](https://mlsanity.com/paper/2210.09638/) (2022)

## Abstract (arXiv)

In this paper, we aim to understand the generalization properties of generative adversarial networks (GANs) from a new perspective of privacy protection. Theoretically, we prove that a differentially private learning algorithm used for training the GAN does not overfit to a certain degree, i.e., the generalization gap can be bounded. Moreover, some recent works, such as the Bayesian GAN, can be re-interpreted based on our theoretical insight from privacy protection. Quantitatively, to evaluate the information leakage of well-trained GAN models, we perform various membership attacks on these models. The results show that previous Lipschitz regularization techniques are effective in not only reducing the generalization gap but also alleviating the information leakage of the training dataset.