зеркало из https://github.com/microsoft/privGAN.git
37e3484baf | ||
---|---|---|
classifier | ||
privacygan | ||
.gitignore | ||
CODE_OF_CONDUCT.md | ||
LICENSE | ||
MNIST_down_tf2.ipynb | ||
PrivGAN_lfw_tf2.ipynb | ||
PrivGAN_mnist_fash_tf2.ipynb | ||
PrivGAN_mnist_tf2.ipynb | ||
PrivGan_CIFAR_tf2.ipynb | ||
README.md | ||
SECURITY.md | ||
contributing.md | ||
requirements.txt | ||
setup.py |
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
Contact
Copyright
Copyright (c) Microsoft Corporation.