PrivGAN: Protecting GANs from membership inference attacks at low cost

Перейти к файлу

Sumit Mukherjee 37e3484baf Updating Read me		2021-01-18 22:50:03 -08:00
classifier	Refactored codebase w.r.t comments from Sumit	2020-08-17 21:22:17 -07:00
privacygan	Refactored the code to put dataset specific gans into different directories	2020-07-30 21:44:45 -07:00
.gitignore	Initial commit	2020-07-14 21:55:37 +00:00
CODE_OF_CONDUCT.md	Initial CODE_OF_CONDUCT.md commit	2020-07-14 14:55:47 -07:00
LICENSE	Initial LICENSE commit	2020-07-14 14:55:47 -07:00
MNIST_down_tf2.ipynb	Refactored codebase w.r.t comments from Sumit	2020-08-17 21:22:17 -07:00
PrivGAN_lfw_tf2.ipynb	Refactored the code to put dataset specific gans into different directories	2020-07-30 21:44:45 -07:00
PrivGAN_mnist_fash_tf2.ipynb	Refactored the code to put dataset specific gans into different directories	2020-07-30 21:44:45 -07:00
PrivGAN_mnist_tf2.ipynb	Refactored the code to put dataset specific gans into different directories	2020-07-30 21:44:45 -07:00
PrivGan_CIFAR_tf2.ipynb	Removed output from another notebook	2020-08-11 01:40:53 -07:00
README.md	Updating Read me	2021-01-18 22:50:03 -08:00
SECURITY.md	Initial SECURITY.md commit	2020-07-14 14:55:48 -07:00
contributing.md	Initial commit	2020-07-14 14:58:19 -07:00
requirements.txt	Changes required to push package to PyPI	2020-10-13 00:52:09 -07:00
setup.py	Changes required to push package to PyPI	2020-10-13 00:52:09 -07:00

README.md

privGAN

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 Accepted at PETS 2021

Version information

Python 3.7.3
Numpy 1.16.2
Pandas 0.25.3
Tqdm 4.38.0
Keras 2.2.4
Scipy 1.1.0
Tensorflow 1.14.0
Scikit-learn 0.20.3

Notebooks comparing white-box attack accuracy of privGAN and GAN on verious datasets

PrivGAN_mnist.ipynb
PrivGAN_mnist_fashion.ipynb
PrivGAN_lfw.ipynb
PrivGAN_cifar.ipynb

Notebooks comparing performance on downstream classification tasks

MNIST_down.ipynb

Installation

Contribution

Please review the link here to know code of conduct https://opensource.microsoft.com/codeofconduct . Before submitting a pull request please remove all output from your notebooks by going to Cell -> All Output -> Clear