Scale-Invariant Adversarial Attack against Arbitrary-scale Super-resolution
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917954473426944 |
|---|---|
| author | Huang, Yihao Luo, Xin Guo, Qing Juefei-Xu, Felix Jia, Xiaojun Miao, Weikai Pu, Geguang Liu, Yang |
| author_facet | Huang, Yihao Luo, Xin Guo, Qing Juefei-Xu, Felix Jia, Xiaojun Miao, Weikai Pu, Geguang Liu, Yang |
| contents | The advent of local continuous image function (LIIF) has garnered significant attention for arbitrary-scale super-resolution (SR) techniques. However, while the vulnerabilities of fixed-scale SR have been assessed, the robustness of continuous representation-based arbitrary-scale SR against adversarial attacks remains an area warranting further exploration. The elaborately designed adversarial attacks for fixed-scale SR are scale-dependent, which will cause time-consuming and memory-consuming problems when applied to arbitrary-scale SR. To address this concern, we propose a simple yet effective ``scale-invariant'' SR adversarial attack method with good transferability, termed SIAGT. Specifically, we propose to construct resource-saving attacks by exploiting finite discrete points of continuous representation. In addition, we formulate a coordinate-dependent loss to enhance the cross-model transferability of the attack. The attack can significantly deteriorate the SR images while introducing imperceptible distortion to the targeted low-resolution (LR) images. Experiments carried out on three popular LIIF-based SR approaches and four classical SR datasets show remarkable attack performance and transferability of SIAGT. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_04385 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Scale-Invariant Adversarial Attack against Arbitrary-scale Super-resolution Huang, Yihao Luo, Xin Guo, Qing Juefei-Xu, Felix Jia, Xiaojun Miao, Weikai Pu, Geguang Liu, Yang Computer Vision and Pattern Recognition The advent of local continuous image function (LIIF) has garnered significant attention for arbitrary-scale super-resolution (SR) techniques. However, while the vulnerabilities of fixed-scale SR have been assessed, the robustness of continuous representation-based arbitrary-scale SR against adversarial attacks remains an area warranting further exploration. The elaborately designed adversarial attacks for fixed-scale SR are scale-dependent, which will cause time-consuming and memory-consuming problems when applied to arbitrary-scale SR. To address this concern, we propose a simple yet effective ``scale-invariant'' SR adversarial attack method with good transferability, termed SIAGT. Specifically, we propose to construct resource-saving attacks by exploiting finite discrete points of continuous representation. In addition, we formulate a coordinate-dependent loss to enhance the cross-model transferability of the attack. The attack can significantly deteriorate the SR images while introducing imperceptible distortion to the targeted low-resolution (LR) images. Experiments carried out on three popular LIIF-based SR approaches and four classical SR datasets show remarkable attack performance and transferability of SIAGT. |
| title | Scale-Invariant Adversarial Attack against Arbitrary-scale Super-resolution |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.04385 |