paper-with-me

홈 › Papers

Private GANs, Revisited

2023-02-06 · Alex Bie, Gautam Kamath, Guojun Zhang

We show that the canonical approach for training differentially private GANs -- updating the discriminator with differentially private stochastic gradient descent (DPSGD) -- can yield significantly improved results after modifications to training. Specifically, we propose that existing instantiations of this approach neglect to consider how adding noise only to discriminator updates inhibits discriminator training, disrupting the balance between the generator and discriminator necessary for successful GAN training. We show that a simple fix -- taking more discriminator steps between generator steps -- restores parity between the generator and discriminator and improves results. Additionally, with the goal of restoring parity, we experiment with other modifications -- namely, large batch sizes and adaptive discriminator update frequency -- to improve discriminator training and see further improvements in generation quality. Our results demonstrate that on standard image synthesis benchmarks, DPSGD outperforms all alternative GAN privatization schemes. Code: https://github.com/alexbie98/dpgan-revisit.

📄 PDF Abstract BibTeX arXiv:2302.02936

Code (1)

alexbie98/dpgan-revisit 공식 구현 pytorch

Tasks

Image Generation

Similar Papers 제목 키워드 기반

Differentially Private Matrix Completion Revisited

2017-12-28 · ICML 2018 7 · Prateek Jain, Om Thakkar, Abhradeep Thakurta

We provide the first provably joint differentially private algorithm with formal utility guarantees for the problem of user-level privacy-preserving collaborative filtering. Our algorithm is based on the Frank-Wolfe meth…

Collaborative FilteringMatrix CompletionPrivacy Preserving

Private Post-GAN Boosting

2020-07-23 · ICLR 2021 1 · Marcel Neunhoeffer, Zhiwei Steven Wu, Cynthia Dwork

Differentially private GANs have proven to be a promising approach for generating realistic synthetic data without compromising the privacy of individuals. Due to the privacy-protective noise introduced in the training, …

Using Autoencoders on Differentially Private Federated Learning GANs

2022-06-24 · Gregor Schram, Rui Wang, Kaitai Liang

Machine learning has been applied to almost all fields of computer science over the past decades. The introduction of GANs allowed for new possibilities in fields of medical research and text prediction. However, these n…

AvgDenoisingFederated Learning

Differentially Private Empirical Risk Minimization Revisited: Faster and More General

2018-02-14 · NeurIPS 2017 12 · Di Wang, Minwei Ye, Jinhui Xu

In this paper we study the differentially private Empirical Risk Minimization (ERM) problem in different settings. For smooth (strongly) convex loss function with or without (non)-smooth regularization, we give algorithm…

On the MIA Vulnerability Gap Between Private GANs and Diffusion Models

2025-09-03 · Ilana Sebag, Jean-Yves Franceschi, Alain Rakotomamonjy, Alexandre Allauzen 외 arxiv

Generative Adversarial Networks (GANs) and diffusion models have emerged as leading approaches for high-quality image synthesis. While both can be trained under differential privacy (DP) to protect sensitive data, their …