8000 GitHub - localhost1025/BaRT-demo: Testing HopSkipJumpAttack against Barrage of Random Transforms Defense method
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

localhost1025/BaRT-demo

Repository files navigation

BaRT-demo

Testing adversarial images against Barrage of Random Transforms Defense method

Original paper:

http://openaccess.thecvf.com/content_CVPR_2019/html/Raff_Barrage_of_Random_Transforms_for_Adversarially_Robust_Defense_CVPR_2019_paper.html

BaRT repo:

https://github.com/XttyCTL9/BaRTDefense

This project was built in:
Tensorflow 1.14.0
scipy 1.1.0
scikit-image 0.16.2
Pillow 6.0.0

Checkpoint downloaded from:

https://pan.baidu.com/s/1yAqmqfSODylaZQuF8nZ3vw

Adversarial images:

There are 10 adversarial images generated under the adversarial_images_resnet50 folder.

These adversarial images are generated using the Trusted-AI adversarial-robustness-toolbox.

The attack method was performed using the HopSkipJump attack on resnet_v2_50 using the untargeted attack mode.

About

Testing HopSkipJumpAttack against Barrage of Random Transforms Defense method

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published
0