MagDR: Mask-Guided Detection and Reconstruction for Defending Deepfakes
Abstract
Deepfakes raised serious concerns on the authenticity of visual contents. Prior works revealed the possibility to disrupt deepfakes by adding adversarial perturbations to the source data, but we argue that the threat has not been eliminated yet. This paper presents MagDR, a mask-guided detection and reconstruction pipeline for defending deepfakes from adversarial attacks. MagDR starts with a detection module that defines a few criteria to judge the abnormality of the output of deepfakes, and then uses it to guide an learnable reconstruction procedure. Adaptive masks are extracted to capture the change in local facial regions. In experiments, MagDR defends three main tasks of deepfakes, and the learned reconstruction pipeline transfers across input data, showing promising performance in defending both black-box and white-box attacks.
Cite
Text
Chen et al. "MagDR: Mask-Guided Detection and Reconstruction for Defending Deepfakes." Conference on Computer Vision and Pattern Recognition, 2021. doi:10.1109/CVPR46437.2021.00890Markdown
[Chen et al. "MagDR: Mask-Guided Detection and Reconstruction for Defending Deepfakes." Conference on Computer Vision and Pattern Recognition, 2021.](https://mlanthology.org/cvpr/2021/chen2021cvpr-magdr/) doi:10.1109/CVPR46437.2021.00890BibTeX
@inproceedings{chen2021cvpr-magdr,
title = {{MagDR: Mask-Guided Detection and Reconstruction for Defending Deepfakes}},
author = {Chen, Zhikai and Xie, Lingxi and Pang, Shanmin and He, Yong and Zhang, Bo},
booktitle = {Conference on Computer Vision and Pattern Recognition},
year = {2021},
pages = {9014-9023},
doi = {10.1109/CVPR46437.2021.00890},
url = {https://mlanthology.org/cvpr/2021/chen2021cvpr-magdr/}
}