Skip to content
/ EARL Public
forked from FenHua/EARL

video_attack; Efficient Sparse Attacks on Videos using Reinforcement Learning

Notifications You must be signed in to change notification settings

gcxamy/EARL

 
 

Repository files navigation

EARL

This repository provides a simple implementation of the work “Efficient Sparse Attacks on Videos using Reinforcement Learning”

Example:

Demo:

Here, we provide 5 video clips in folder "dataset_numpy", you can run the following script and observe the effect:

python un_attack_show.py   # untargeted attack

or

python T_attack_show.py    # targeted attack

Threat models:

The video classification model, please refer to project https://github.com/FenHua/action-recognition

You can train the recognition model with your own data, and use the video attack method to attack them.

Please cite:

@inproceedings{yan2021efficient,
  title={Efficient Sparse Attacks on Videos using Reinforcement Learning},
  author={Yan, Huanqian and Wei, Xingxing},
  booktitle={Proceedings of the 29th ACM International Conference on Multimedia},
  pages={2326--2334},
  year={2021}
}

About

video_attack; Efficient Sparse Attacks on Videos using Reinforcement Learning

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 96.4%
  • Jupyter Notebook 3.5%
  • Shell 0.1%