Anti-Inpainting: A Proactive Defense Approach against Malicious Diffusion-based Inpainters under Unknown Conditions
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911087761293312 |
|---|---|
| author | Guo, Yimao Qu, Zuomin Lu, Wei Luo, Xiangyang |
| author_facet | Guo, Yimao Qu, Zuomin Lu, Wei Luo, Xiangyang |
| contents | With the increasing prevalence of diffusion-based malicious image manipulation, existing proactive defense methods struggle to safeguard images against tampering under unknown conditions. To address this, we propose Anti-Inpainting, a proactive defense approach that achieves protection comprising three novel modules. First, we introduce a multi-level deep feature extractor to obtain intricate features from the diffusion denoising process, enhancing protective effectiveness. Second, we design a multi-scale, semantic-preserving data augmentation technique to enhance the transferability of adversarial perturbations across unknown conditions. Finally, we propose a selection-based distribution deviation optimization strategy to bolster protection against manipulations guided by diverse random seeds. Extensive experiments on InpaintGuardBench and CelebA-HQ demonstrate that Anti-Inpainting effectively defends against diffusion-based inpainters under unknown conditions. Additionally, our approach demonstrates robustness against various image purification methods and transferability across different diffusion model versions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_13023 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Anti-Inpainting: A Proactive Defense Approach against Malicious Diffusion-based Inpainters under Unknown Conditions Guo, Yimao Qu, Zuomin Lu, Wei Luo, Xiangyang Computer Vision and Pattern Recognition Artificial Intelligence Multimedia With the increasing prevalence of diffusion-based malicious image manipulation, existing proactive defense methods struggle to safeguard images against tampering under unknown conditions. To address this, we propose Anti-Inpainting, a proactive defense approach that achieves protection comprising three novel modules. First, we introduce a multi-level deep feature extractor to obtain intricate features from the diffusion denoising process, enhancing protective effectiveness. Second, we design a multi-scale, semantic-preserving data augmentation technique to enhance the transferability of adversarial perturbations across unknown conditions. Finally, we propose a selection-based distribution deviation optimization strategy to bolster protection against manipulations guided by diverse random seeds. Extensive experiments on InpaintGuardBench and CelebA-HQ demonstrate that Anti-Inpainting effectively defends against diffusion-based inpainters under unknown conditions. Additionally, our approach demonstrates robustness against various image purification methods and transferability across different diffusion model versions. |
| title | Anti-Inpainting: A Proactive Defense Approach against Malicious Diffusion-based Inpainters under Unknown Conditions |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Multimedia |
| url | https://arxiv.org/abs/2505.13023 |