Skip to content

vcl-iisc/data_free_adversarial_defense

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

DAD: Data-free Adversarial Defense at Test Time (WACV 2022) - Official Implementation

Paper link: https://openaccess.thecvf.com/content/WACV2022/papers/Nayak_DAD_Data-Free_Adversarial_Defense_at_Test_Time_WACV_2022_paper.pdf

Poster: https://drive.google.com/file/d/16VvThgTOMY28dMTlk4-NA9O9WQMyWLEc/view

Project webpage: https://sites.google.com/view/dad-wacv22


Method Overview

technique overview


Dependencies

  • tqdm
  • torch
  • numpy
  • torchattacks

Evaluating Combined Performance (Correction + Detection):

./scripts/combined.sh


Citation:

If you use this code, please cite our work as:

    @inproceedings{
        nayak2021_DAD,
        title={DAD: Data-free Adversarial Defense at Test Time},
        author={Nayak, G. K., Rawal, R., and Chakraborty, A.},
        booktitle={IEEE Winter Conference on Applications of 
        Computer Vision},
        year={2022}
    }

Acknowledgements

This repo borrows code from Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation and High Frequency Component Helps Explain the Generalization of Convolutional Neural Networks

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published