Skip to content
/ AdvAE Public

Purifying Adversarial Perturbation with Adversarially Trained Auto-encoders

License

Notifications You must be signed in to change notification settings

lihebi/AdvAE

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Adversarially trained auto-encoders

We propose to iteratively adversarially train an external auto-encoder to protect a vulnerable base classifier.

The algorithm is implemented in four frameworks, source code can be found in the following folders:

  • python: using tensorflow v1 and keras, most complete implementation including BPDA
  • tf2: using tensorflow v2
  • pytorch: using pytorch
  • julia: using Julia and Flux, best code quality, recommanded

License of code: MIT

About

Purifying Adversarial Perturbation with Adversarially Trained Auto-encoders

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Languages