Warfare:Breaking the Watermark Protection of AI-Generated Content
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916594025758720 |
|---|---|
| author | Li, Guanlin Chen, Yifei Zhang, Jie Guo, Shangwei Qiu, Han Wang, Guoyin Li, Jiwei Zhang, Tianwei |
| author_facet | Li, Guanlin Chen, Yifei Zhang, Jie Guo, Shangwei Qiu, Han Wang, Guoyin Li, Jiwei Zhang, Tianwei |
| contents | AI-Generated Content (AIGC) is rapidly expanding, with services using advanced generative models to create realistic images and fluent text. Regulating such content is crucial to prevent policy violations, such as unauthorized commercialization or unsafe content distribution. Watermarking is a promising solution for content attribution and verification, but we demonstrate its vulnerability to two key attacks: (1) Watermark removal, where adversaries erase embedded marks to evade regulation, and (2) Watermark forging, where they generate illicit content with forged watermarks, leading to misattribution. We propose Warfare, a unified attack framework leveraging a pre-trained diffusion model for content processing and a generative adversarial network for watermark manipulation. Evaluations across datasets and embedding setups show that Warfare achieves high success rates while preserving content quality. We further introduce Warfare-Plus, which enhances efficiency without compromising effectiveness. The code can be found in https://github.com/GuanlinLee/warfare. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2310_07726 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Warfare:Breaking the Watermark Protection of AI-Generated Content Li, Guanlin Chen, Yifei Zhang, Jie Guo, Shangwei Qiu, Han Wang, Guoyin Li, Jiwei Zhang, Tianwei Computer Vision and Pattern Recognition Artificial Intelligence AI-Generated Content (AIGC) is rapidly expanding, with services using advanced generative models to create realistic images and fluent text. Regulating such content is crucial to prevent policy violations, such as unauthorized commercialization or unsafe content distribution. Watermarking is a promising solution for content attribution and verification, but we demonstrate its vulnerability to two key attacks: (1) Watermark removal, where adversaries erase embedded marks to evade regulation, and (2) Watermark forging, where they generate illicit content with forged watermarks, leading to misattribution. We propose Warfare, a unified attack framework leveraging a pre-trained diffusion model for content processing and a generative adversarial network for watermark manipulation. Evaluations across datasets and embedding setups show that Warfare achieves high success rates while preserving content quality. We further introduce Warfare-Plus, which enhances efficiency without compromising effectiveness. The code can be found in https://github.com/GuanlinLee/warfare. |
| title | Warfare:Breaking the Watermark Protection of AI-Generated Content |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2310.07726 |