Skip to content

Latest commit

 

History

History
53 lines (32 loc) · 1.69 KB

README.md

File metadata and controls

53 lines (32 loc) · 1.69 KB
Raw

Admix

This repository contains code to reproduce results from the paper:

Admix: Enhancing the Transferability of Adversarial Attacks (ICCV 2021)

Xiaosen Wang, Xuanran He, Jingdong Wang, Kun He

We also include the torch version code in the framework TransferAttack.

Requirements

  • Python >= 3.6.5
  • Tensorflow >= 1.12.0
  • Numpy >= 1.15.4
  • opencv >= 3.4.2
  • scipy > 1.1.0
  • pandas >= 1.0.1
  • imageio >= 2.6.1

Qucik Start

Prepare the data and models

You should download the data and pretrained models and place the data and pretrained models in dev_data/ and models/, respectively.

Admix

All the provided codes generate adversarial examples on inception_v3 model. If you want to attack other models, replace the model in graph and batch_grad function and load such models in main function.

Runing attack

Taking Admix attack for example, you can run this attack as following:

CUDA_VISIBLE_DEVICES=gpuid python mi_admix.py

Evaluating the attack

The generated adversarial examples would be stored in directory ./outputs. Then run the file simple_eval.py to evaluate the success rate of each model used in the paper:

CUDA_VISIBLE_DEVICES=gpuid python simple_eval.py

Acknowledgments

Code refers to SI-NI-FGSM and Variance Tuning.

Contact

Questions and suggestions can be sent to xswanghuster@gmail.com.