Skip to content
/ Pseudo-Differentiable-JPEG Public
forked from ChaoningZhang/Pseudo-Differentiable-JPEG

Official repository for the paper "Towards Robust Data Hiding Against (JPEG) Compression: A Pseudo-Differentiable Deep Learning Approach".

0 stars 2 forks Branches Tags Activity
Star
Notifications You must be signed in to change notification settings

jj199603/Pseudo-Differentiable-JPEG

BranchesTags
 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

1 Commit
model
model
 
 
modules
modules
 
 
noise_layers
noise_layers
 
 
runfiles
runfiles
 
 
scripts_adv_loss
scripts_adv_loss
 
 
.gitignore
.gitignore
 
 
README.md
README.md
 
 
average_meter.py
average_meter.py
 
 
main.py
main.py
 
 
noise_argparser.py
noise_argparser.py
 
 
oops_dataset.py
oops_dataset.py
 
 
options.py
options.py
 
 
tensorboard_logger.py
tensorboard_logger.py
 
 
test_model.py
test_model.py
 
 
train.py
train.py
 
 
utils.py
utils.py
 
 
validate-trained-models.py
validate-trained-models.py
 
 
validate-trained-models_diff_corruptions.py
validate-trained-models_diff_corruptions.py
 
 
validate-trained-models_diff_jpeg2000_levels.py
validate-trained-models_diff_jpeg2000_levels.py
 
 
validate-trained-models_diff_jpeg_levels.py
validate-trained-models_diff_jpeg_levels.py
 
 
validate-trained-models_diff_webp_levels.py
validate-trained-models_diff_webp_levels.py
 
 
vgg_loss.py
vgg_loss.py
 
 

Repository files navigation

Towards Robust Data Hiding Against (JPEG) Compression: A Pseudo-Differentiable Deep Learning Approach

Official pytorch code for the paper "Towards Robust Data Hiding Against (JPEG) Compression: A Pseudo-Differentiable Deep Learning Approach" by Chaoning Zhang*, Adil Karjauv*, Philipp Benz*, and In So Kweon (*Equal Contribution).

Experiments

In order to run the experiments, just use the scripts from the "scripts_adv_loss" folder. For example:

bash run_jpeg2.sh

Note

More detailed instructions about the code are coming soon.

About

Official repository for the paper "Towards Robust Data Hiding Against (JPEG) Compression: A Pseudo-Differentiable Deep Learning Approach".

Resources

Readme
Activity

Stars

0 stars

Watchers

0 watching

Forks

0 forks
Report repository

Releases

No releases published

Packages

No packages published

Languages

  • Python 96.3%
  • Shell 3.7%