WMCopier: Forging Invisible Image Watermarks on Arbitrary Images
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915572791377920 |
|---|---|
| author | Dong, Ziping Shuai, Chao Ba, Zhongjie Cheng, Peng Qin, Zhan Wang, Qinglong Ren, Kui |
| author_facet | Dong, Ziping Shuai, Chao Ba, Zhongjie Cheng, Peng Qin, Zhan Wang, Qinglong Ren, Kui |
| contents | Invisible Image Watermarking is crucial for ensuring content provenance and accountability in generative AI. While Gen-AI providers are increasingly integrating invisible watermarking systems, the robustness of these schemes against forgery attacks remains poorly characterized. This is critical, as forging traceable watermarks onto illicit content leads to false attribution, potentially harming the reputation and legal standing of Gen-AI service providers who are not responsible for the content. In this work, we propose WMCopier, an effective watermark forgery attack that operates without requiring any prior knowledge of or access to the target watermarking algorithm. Our approach first models the target watermark distribution using an unconditional diffusion model, and then seamlessly embeds the target watermark into a non-watermarked image via a shallow inversion process. We also incorporate an iterative optimization procedure that refines the reconstructed image to further trade off the fidelity and forgery efficiency. Experimental results demonstrate that WMCopier effectively deceives both open-source and closed-source watermark systems (e.g., Amazon's system), achieving a significantly higher success rate than existing methods. Additionally, we evaluate the robustness of forged samples and discuss the potential defenses against our attack. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_22330 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | WMCopier: Forging Invisible Image Watermarks on Arbitrary Images Dong, Ziping Shuai, Chao Ba, Zhongjie Cheng, Peng Qin, Zhan Wang, Qinglong Ren, Kui Cryptography and Security Computer Vision and Pattern Recognition Invisible Image Watermarking is crucial for ensuring content provenance and accountability in generative AI. While Gen-AI providers are increasingly integrating invisible watermarking systems, the robustness of these schemes against forgery attacks remains poorly characterized. This is critical, as forging traceable watermarks onto illicit content leads to false attribution, potentially harming the reputation and legal standing of Gen-AI service providers who are not responsible for the content. In this work, we propose WMCopier, an effective watermark forgery attack that operates without requiring any prior knowledge of or access to the target watermarking algorithm. Our approach first models the target watermark distribution using an unconditional diffusion model, and then seamlessly embeds the target watermark into a non-watermarked image via a shallow inversion process. We also incorporate an iterative optimization procedure that refines the reconstructed image to further trade off the fidelity and forgery efficiency. Experimental results demonstrate that WMCopier effectively deceives both open-source and closed-source watermark systems (e.g., Amazon's system), achieving a significantly higher success rate than existing methods. Additionally, we evaluate the robustness of forged samples and discuss the potential defenses against our attack. |
| title | WMCopier: Forging Invisible Image Watermarks on Arbitrary Images |
| topic | Cryptography and Security Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.22330 |