Protective Perturbations against Unauthorized Data Usage in Diffusion-based Image Generation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916543277826048 |
|---|---|
| author | Peng, Sen Yang, Jijia Wang, Mingyue He, Jianfei Jia, Xiaohua |
| author_facet | Peng, Sen Yang, Jijia Wang, Mingyue He, Jianfei Jia, Xiaohua |
| contents | Diffusion-based text-to-image models have shown immense potential for various image-related tasks. However, despite their prominence and popularity, customizing these models using unauthorized data also brings serious privacy and intellectual property issues. Existing methods introduce protective perturbations based on adversarial attacks, which are applied to the customization samples. In this systematization of knowledge, we present a comprehensive survey of protective perturbation methods designed to prevent unauthorized data usage in diffusion-based image generation. We establish the threat model and categorize the downstream tasks relevant to these methods, providing a detailed analysis of their designs. We also propose a completed evaluation framework for these perturbation techniques, aiming to advance research in this field. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_18791 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Protective Perturbations against Unauthorized Data Usage in Diffusion-based Image Generation Peng, Sen Yang, Jijia Wang, Mingyue He, Jianfei Jia, Xiaohua Computer Vision and Pattern Recognition Diffusion-based text-to-image models have shown immense potential for various image-related tasks. However, despite their prominence and popularity, customizing these models using unauthorized data also brings serious privacy and intellectual property issues. Existing methods introduce protective perturbations based on adversarial attacks, which are applied to the customization samples. In this systematization of knowledge, we present a comprehensive survey of protective perturbation methods designed to prevent unauthorized data usage in diffusion-based image generation. We establish the threat model and categorize the downstream tasks relevant to these methods, providing a detailed analysis of their designs. We also propose a completed evaluation framework for these perturbation techniques, aiming to advance research in this field. |
| title | Protective Perturbations against Unauthorized Data Usage in Diffusion-based Image Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2412.18791 |