Don't FREAK Out: A Frequency-Inspired Approach to Detecting Backdoor Poisoned Samples in DNNs
Abstract
In this paper we investigate the frequency sensitivity of Deep Neural Networks (DNNs) when presented with clean samples versus poisoned samples. Our analysis shows significant disparities in frequency sensitivity between these two types of samples. Building on these findings, we propose FREAK, a frequency-based poisoned sample detection algorithm that is simple yet effective. Our experimental results demonstrate the efficacy of FREAK not only against frequency backdoor attacks but also against some spatial attacks. Our work is just the first step in leveraging these insights. We believe that our analysis and proposed defense mechanism will provide a foundation for future research and development of backdoor defenses.
Cite
Text
Hammoud et al. "Don't FREAK Out: A Frequency-Inspired Approach to Detecting Backdoor Poisoned Samples in DNNs." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2023. doi:10.1109/CVPRW59228.2023.00230Markdown
[Hammoud et al. "Don't FREAK Out: A Frequency-Inspired Approach to Detecting Backdoor Poisoned Samples in DNNs." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2023.](https://mlanthology.org/cvprw/2023/hammoud2023cvprw-don/) doi:10.1109/CVPRW59228.2023.00230BibTeX
@inproceedings{hammoud2023cvprw-don,
title = {{Don't FREAK Out: A Frequency-Inspired Approach to Detecting Backdoor Poisoned Samples in DNNs}},
author = {Hammoud, Hasan Abed Al Kader and Bibi, Adel and Torr, Philip H. S. and Ghanem, Bernard},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
year = {2023},
pages = {2338-2345},
doi = {10.1109/CVPRW59228.2023.00230},
url = {https://mlanthology.org/cvprw/2023/hammoud2023cvprw-don/}
}