FreqMark: Invisible Image Watermarking via Frequency Based Optimization in Latent Space
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913565734076416 |
|---|---|
| author | Guo, Yiyang Li, Ruizhe Hui, Mude Guo, Hanzhong Zhang, Chen Cai, Chuangjian Wan, Le Wang, Shangfei |
| author_facet | Guo, Yiyang Li, Ruizhe Hui, Mude Guo, Hanzhong Zhang, Chen Cai, Chuangjian Wan, Le Wang, Shangfei |
| contents | Invisible watermarking is essential for safeguarding digital content, enabling copyright protection and content authentication. However, existing watermarking methods fall short in robustness against regeneration attacks. In this paper, we propose a novel method called FreqMark that involves unconstrained optimization of the image latent frequency space obtained after VAE encoding. Specifically, FreqMark embeds the watermark by optimizing the latent frequency space of the images and then extracts the watermark through a pre-trained image encoder. This optimization allows a flexible trade-off between image quality with watermark robustness and effectively resists regeneration attacks. Experimental results demonstrate that FreqMark offers significant advantages in image quality and robustness, permits flexible selection of the encoding bit number, and achieves a bit accuracy exceeding 90% when encoding a 48-bit hidden message under various attack scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_20824 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | FreqMark: Invisible Image Watermarking via Frequency Based Optimization in Latent Space Guo, Yiyang Li, Ruizhe Hui, Mude Guo, Hanzhong Zhang, Chen Cai, Chuangjian Wan, Le Wang, Shangfei Cryptography and Security Computer Vision and Pattern Recognition Machine Learning Invisible watermarking is essential for safeguarding digital content, enabling copyright protection and content authentication. However, existing watermarking methods fall short in robustness against regeneration attacks. In this paper, we propose a novel method called FreqMark that involves unconstrained optimization of the image latent frequency space obtained after VAE encoding. Specifically, FreqMark embeds the watermark by optimizing the latent frequency space of the images and then extracts the watermark through a pre-trained image encoder. This optimization allows a flexible trade-off between image quality with watermark robustness and effectively resists regeneration attacks. Experimental results demonstrate that FreqMark offers significant advantages in image quality and robustness, permits flexible selection of the encoding bit number, and achieves a bit accuracy exceeding 90% when encoding a 48-bit hidden message under various attack scenarios. |
| title | FreqMark: Invisible Image Watermarking via Frequency Based Optimization in Latent Space |
| topic | Cryptography and Security Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2410.20824 |