https://github.com/alps-lab/dpgan

Differentially private release of semantic rich data
https://github.com/alps-lab/dpgan

Last synced: 3 months ago
JSON representation

Differentially private release of semantic rich data

• Host: GitHub
• URL: https://github.com/alps-lab/dpgan
• Owner: alps-lab
• Created: 2018-03-08T22:33:41.000Z (over 6 years ago)
• Default Branch: master
• Last Pushed: 2021-06-17T15:34:02.000Z (over 3 years ago)
• Last Synced: 2024-04-08T02:26:59.766Z (7 months ago)
• Language: Python
• Size: 75.2 KB
• Stars: 35
• Watchers: 1
• Forks: 11
• Open Issues: 2
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

• awesome-data-synthesis - DP-GAN - Differentially private release of semantic rich data - [Paper](https://arxiv.org/abs/1801.01594) (Data-driven methods / Tabular)

README

        
### DPGAN: Differentially Private Releasing via Deep Generative Models

#### Description

This is the implementaiton of "Differentially Private Releasing via Deep Generative Models", which trains GAN models in a differentially private manner such that the models can be used to synthesize data for downstream tasks.

#### Citation

If you used the source code, please cite: Xinyang Zhang, Shouling Ji, and Ting Wang, Differentially Private Releasing via Deep Generative Model, arXiv e-prints, 2018.

#### Datasets

The current implementation supports the datasets including MNIST, CelebA, and LSUN. 

#### Usage

Check the folder dpgan/src/dp.