Metadata-Version: 2.1
Name: privGan
Version: 1.0
Summary: Privacy protected GAN for image data
Home-page: https://github.com/microsoft/privGAN
Author: Sumit Mukherjee, Nabajyoti Patowary
Author-email: privgan@microsoft.com
License: MIT
Platform: UNKNOWN
Description-Content-Type: text/markdown
Requires-Dist: numpy (>=1.16.2)
Requires-Dist: pandas (>=0.25.3)
Requires-Dist: tqdm (>=4.38.0)
Requires-Dist: keras (>=2.2.4)
Requires-Dist: scipy (>=1.1.0)
Requires-Dist: matplotlib (>=3.3.0)
Provides-Extra: tf
Requires-Dist: tensorflow (>=1.14.0) ; extra == 'tf'

This repository contains the source code for PrivGan - a novel approach     for deterring membership inference attacks on GAN generated synthetic medical data.Currently,     the repository contains the jupyter notebooks for various datasets. We will be converting     the code into a library in the future. Please visit our paper     "PrivGAN: Protecting GANs from membership inference attacks at low cost" [ArXiv Link](https://arxiv.org/abs/2001.00071) submitted at PETS 2021.


