Skip to content
The code for CVPR2019 (ComDefend: An Efficient Image Compression Model to Defend Adversarial Examples)
Python
Branch: master
Clone or download
Latest commit 08862d2 May 16, 2019
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
.idea 提交文件 Mar 31, 2019
__pycache__ 提交文件 Mar 31, 2019
attack_image 提交文件 Mar 31, 2019
checkpoints 提交文件 Mar 31, 2019
clean_image 提交文件 Mar 31, 2019
com_imagenet_temp 提交文件 Mar 30, 2019
defend_image 提交文件 Mar 31, 2019
temp_imagenet 提交文件 Mar 30, 2019
README.md Update README.md May 16, 2019
Resnet_imagenet.py 提交文件 Mar 31, 2019
compression_imagenet.py 提交文件 Mar 31, 2019
compression_mnist.py 提交文件 Mar 31, 2019
dev.csv 提交文件 Mar 31, 2019
processer.py 提交文件 Mar 31, 2019

README.md

Comdefend

The code for CVPR2019 (ComDefend: An Efficient Image Compression Model to Defend Adversarial Examples) paper The pure tensorflow of code is released in the link

Environmental configuration

tensorflow>=1.1
python3
canton(pip install canton)

The keras and pytorch of the code will be released soon.

Description

clean_image: we select 7 clean images which are classified correctly by the classifier
attack_image: we select 7 adversarial images which are attacked by the FGSM method
defend_image: we use the Comdefend to deal with 7 adversarial images
chackpoints: the model parameters
com_imagenet_temp, temp_imagenet: the temporary files of the Comdefend
dev.csv: correspondence between images and labels
Resnet_imagenet.py: the classifier
compression_imagenet.py: the Comdefend for Imagenet
compression_mnist.py: the Comdefend for fashion_mnist

In addition

E-mail: jiaxiaojun@iie.ac.cn or 1642768580@qq.com

You can’t perform that action at this time.