/Minimizing-AT-samples-for-robustness

Primary LanguagePython

Minimizing-AT-samples-for-robustness

This repository contains the source code of "Minimizing Adversarial Training Samples for Robust Image Classifiers: Analysis and adversarial example Generator Design".

Contents

The repository consists of the following:

  • adversarial_train.py: Code for adversarial training in the method.
  • test_acc.py: Code for performing predictions using the ARF method.
  • generate_and_test.py: Code for adversarial attack.
  • 'new_gan/model/wgan_C_gan.py': Code for new GAN network.
  • 'new_gan/train_gan.py': Code for training new GAN.

Usage

To use the ARF method and comparison methods, follow the instructions below:

  1. Navigate to the Minimizing-AT-samples-for-robustness/ directory.
  2. Run adversarial_train.py to implement adversarial training.
  3. Use test_acc.py to perform predictions using the ARF method.
  4. Use 'new_gan/train_gan.py' to implement GAN training.