Skip to content

a Pytorch implementation of the paper "Generating Adversarial Examples with Adversarial Networks" (advGAN).

Notifications You must be signed in to change notification settings

mathcbc/advGAN_pytorch

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

9 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

advGAN_pytorch

a Pytorch implementation of the paper "Generating Adversarial Examples with Adversarial Networks" (advGAN).

training the target model

python3 train_target_model.py

training the advGAN

python3 main.py

testing adversarial examples

python3 test_adversarial_examples.py

results

attack success rate in the MNIST test set: 99%

NOTE: My implementation is a little different from the paper, because I add a clipping trick.

About

a Pytorch implementation of the paper "Generating Adversarial Examples with Adversarial Networks" (advGAN).

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages