Invisible Image Watermarks Are Provably Removable Using Generative AI
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_ | 1866917824113410048 |
|---|---|
| author | Zhao, Xuandong Zhang, Kexun Su, Zihao Vasan, Saastha Grishchenko, Ilya Kruegel, Christopher Vigna, Giovanni Wang, Yu-Xiang Li, Lei |
| author_facet | Zhao, Xuandong Zhang, Kexun Su, Zihao Vasan, Saastha Grishchenko, Ilya Kruegel, Christopher Vigna, Giovanni Wang, Yu-Xiang Li, Lei |
| contents | Invisible watermarks safeguard images' copyrights by embedding hidden messages only detectable by owners. They also prevent people from misusing images, especially those generated by AI models. We propose a family of regeneration attacks to remove these invisible watermarks. The proposed attack method first adds random noise to an image to destroy the watermark and then reconstructs the image. This approach is flexible and can be instantiated with many existing image-denoising algorithms and pre-trained generative models such as diffusion models. Through formal proofs and extensive empirical evaluations, we demonstrate that pixel-level invisible watermarks are vulnerable to this regeneration attack. Our results reveal that, across four different pixel-level watermarking schemes, the proposed method consistently achieves superior performance compared to existing attack techniques, with lower detection rates and higher image quality. However, watermarks that keep the image semantically similar can be an alternative defense against our attacks. Our finding underscores the need for a shift in research/industry emphasis from invisible watermarks to semantic-preserving watermarks. Code is available at https://github.com/XuandongZhao/WatermarkAttacker |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2306_01953 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Invisible Image Watermarks Are Provably Removable Using Generative AI Zhao, Xuandong Zhang, Kexun Su, Zihao Vasan, Saastha Grishchenko, Ilya Kruegel, Christopher Vigna, Giovanni Wang, Yu-Xiang Li, Lei Cryptography and Security Artificial Intelligence Computer Vision and Pattern Recognition Invisible watermarks safeguard images' copyrights by embedding hidden messages only detectable by owners. They also prevent people from misusing images, especially those generated by AI models. We propose a family of regeneration attacks to remove these invisible watermarks. The proposed attack method first adds random noise to an image to destroy the watermark and then reconstructs the image. This approach is flexible and can be instantiated with many existing image-denoising algorithms and pre-trained generative models such as diffusion models. Through formal proofs and extensive empirical evaluations, we demonstrate that pixel-level invisible watermarks are vulnerable to this regeneration attack. Our results reveal that, across four different pixel-level watermarking schemes, the proposed method consistently achieves superior performance compared to existing attack techniques, with lower detection rates and higher image quality. However, watermarks that keep the image semantically similar can be an alternative defense against our attacks. Our finding underscores the need for a shift in research/industry emphasis from invisible watermarks to semantic-preserving watermarks. Code is available at https://github.com/XuandongZhao/WatermarkAttacker |
| title | Invisible Image Watermarks Are Provably Removable Using Generative AI |
| topic | Cryptography and Security Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2306.01953 |