Fooling the Image Dehazing Models by First Order Gradient
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2023
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914679368974336 |
|---|---|
| author | Gui, Jie Cong, Xiaofeng Peng, Chengwei Tang, Yuan Yan Kwok, James Tin-Yau |
| author_facet | Gui, Jie Cong, Xiaofeng Peng, Chengwei Tang, Yuan Yan Kwok, James Tin-Yau |
| contents | The research on the single image dehazing task has been widely explored. However, as far as we know, no comprehensive study has been conducted on the robustness of the well-trained dehazing models. Therefore, there is no evidence that the dehazing networks can resist malicious attacks. In this paper, we focus on designing a group of attack methods based on first order gradient to verify the robustness of the existing dehazing algorithms. By analyzing the general purpose of image dehazing task, four attack methods are proposed, which are predicted dehazed image attack, hazy layer mask attack, haze-free image attack and haze-preserved attack. The corresponding experiments are conducted on six datasets with different scales. Further, the defense strategy based on adversarial training is adopted for reducing the negative effects caused by malicious attacks. In summary, this paper defines a new challenging problem for the image dehazing area, which can be called as adversarial attack on dehazing networks (AADN). Code and Supplementary Material are available at https://github.com/Xiaofeng-life/AADN Dehazing. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2303_17255 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Fooling the Image Dehazing Models by First Order Gradient Gui, Jie Cong, Xiaofeng Peng, Chengwei Tang, Yuan Yan Kwok, James Tin-Yau Computer Vision and Pattern Recognition Cryptography and Security Image and Video Processing The research on the single image dehazing task has been widely explored. However, as far as we know, no comprehensive study has been conducted on the robustness of the well-trained dehazing models. Therefore, there is no evidence that the dehazing networks can resist malicious attacks. In this paper, we focus on designing a group of attack methods based on first order gradient to verify the robustness of the existing dehazing algorithms. By analyzing the general purpose of image dehazing task, four attack methods are proposed, which are predicted dehazed image attack, hazy layer mask attack, haze-free image attack and haze-preserved attack. The corresponding experiments are conducted on six datasets with different scales. Further, the defense strategy based on adversarial training is adopted for reducing the negative effects caused by malicious attacks. In summary, this paper defines a new challenging problem for the image dehazing area, which can be called as adversarial attack on dehazing networks (AADN). Code and Supplementary Material are available at https://github.com/Xiaofeng-life/AADN Dehazing. |
| title | Fooling the Image Dehazing Models by First Order Gradient |
| topic | Computer Vision and Pattern Recognition Cryptography and Security Image and Video Processing |
| url | https://arxiv.org/abs/2303.17255 |