Skip to content

Allen-piexl/AdvCheck

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

15 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

AdvCheck: Adversarial Examples Detection via Local Gradient Checking

Setup

The code should be run using python 3.6.0, Tensorflow-gpu 2.4.0, Keras 2.4.3, Foolbox 2.3.0, PIL, h5py, and opencv-python

Datasets & Models

Here, we give VGG19 trained under CIFAR-10 as a example.

How to train a perfect model

python cifar_model.py

How to run

  • Show Observations
python attack_observation.py
  • Calculate Local Gradient
python Gen_Features_Vgg19.py
  • Adversarial Detection
python check_peturbations.py

Note

See the paper Adversarial Examples Detection via Local Gradient Checking for more details.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages