Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

Sign up
Appearance settings
/ WDAD Public

Adversarial sample detection based on weak dark textures

License

Notifications You must be signed in to change notification settings

faiimea/WDAD

Folders and files

NameName
Last commit message
Last commit date

Latest commit

History

14 Commits

Repository files navigation

Adversarial sample detection based on weak dark textures

Background

Based on the 42nd PRP scientific research program, this project realizes the function of detecting whether images are antagonistic samples according to their gray-scale texture features.

Usage

Run ./PRP_demo/gui/ui.py to invoke the graphical interface.

Click the button at the top of the interface to select the picture, and the system will automatically detect whether it is a counter sample.

Related Efforts

The attack section is based on the demo of adversarial-attacks-pytorch.

The network is based on resnet50 net.

Maintainer

@faiimea

Contributors

@cfg554

TODO

  • Optimize code structure
  • Optimize GUI interface

License

MIT

About

Adversarial sample detection based on weak dark textures

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 2

AltStyle によって変換されたページ (->オリジナル) /