Adversarial Purification and Fine-tuning for Robust UDC Image Restoration
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910679571628032 |
|---|---|
| author | Song, Zhenbo Zhang, Zhenyuan Zhang, Kaihao Fan, Zhaoxin Lu, Jianfeng |
| author_facet | Song, Zhenbo Zhang, Zhenyuan Zhang, Kaihao Fan, Zhaoxin Lu, Jianfeng |
| contents | This study delves into the enhancement of Under-Display Camera (UDC) image restoration models, focusing on their robustness against adversarial attacks. Despite its innovative approach to seamless display integration, UDC technology faces unique image degradation challenges exacerbated by the susceptibility to adversarial perturbations. Our research initially conducts an in-depth robustness evaluation of deep-learning-based UDC image restoration models by employing several white-box and black-box attacking methods. This evaluation is pivotal in understanding the vulnerabilities of current UDC image restoration techniques. Following the assessment, we introduce a defense framework integrating adversarial purification with subsequent fine-tuning processes. First, our approach employs diffusion-based adversarial purification, effectively neutralizing adversarial perturbations. Then, we apply the fine-tuning methodologies to refine the image restoration models further, ensuring that the quality and fidelity of the restored images are maintained. The effectiveness of our proposed approach is validated through extensive experiments, showing marked improvements in resilience against typical adversarial attacks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_13629 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Adversarial Purification and Fine-tuning for Robust UDC Image Restoration Song, Zhenbo Zhang, Zhenyuan Zhang, Kaihao Fan, Zhaoxin Lu, Jianfeng Image and Video Processing Computer Vision and Pattern Recognition This study delves into the enhancement of Under-Display Camera (UDC) image restoration models, focusing on their robustness against adversarial attacks. Despite its innovative approach to seamless display integration, UDC technology faces unique image degradation challenges exacerbated by the susceptibility to adversarial perturbations. Our research initially conducts an in-depth robustness evaluation of deep-learning-based UDC image restoration models by employing several white-box and black-box attacking methods. This evaluation is pivotal in understanding the vulnerabilities of current UDC image restoration techniques. Following the assessment, we introduce a defense framework integrating adversarial purification with subsequent fine-tuning processes. First, our approach employs diffusion-based adversarial purification, effectively neutralizing adversarial perturbations. Then, we apply the fine-tuning methodologies to refine the image restoration models further, ensuring that the quality and fidelity of the restored images are maintained. The effectiveness of our proposed approach is validated through extensive experiments, showing marked improvements in resilience against typical adversarial attacks. |
| title | Adversarial Purification and Fine-tuning for Robust UDC Image Restoration |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2402.13629 |