Do Modern Post-Hoc Watermarking Methods Beat Broken-Arrows?
Fuente:
arXiv
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910261001060352 |
|---|---|
| author | Gesny, Enoal Giboulot, Eva |
| author_facet | Gesny, Enoal Giboulot, Eva |
| contents | With the rapid proliferation of generative models, such as diffusion models, digital watermarking has emerged as a crucial solution for identifying AI-generated images. Modern post-hoc watermarking schemes use neural networks to achieve an extremely low false-alarm rate while remaining robust to common image transformations. However, there is a lack of comparison between these modern methods and classic ones, particularly in real-world scenarios where robustness and security take precedence over achieving an extremely low false-alarm probability. In this paper, we propose a fair comparison of robustness and security between modern and classic post-hoc watermarking across various types of classic augmentations and recent sophisticated attacks. Our experiments show that, in a realistic scenario, classic watermarking outperforms modern techniques in terms of security while maintaining robustness. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_27135 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Do Modern Post-Hoc Watermarking Methods Beat Broken-Arrows? Gesny, Enoal Giboulot, Eva Cryptography and Security Computer Vision and Pattern Recognition With the rapid proliferation of generative models, such as diffusion models, digital watermarking has emerged as a crucial solution for identifying AI-generated images. Modern post-hoc watermarking schemes use neural networks to achieve an extremely low false-alarm rate while remaining robust to common image transformations. However, there is a lack of comparison between these modern methods and classic ones, particularly in real-world scenarios where robustness and security take precedence over achieving an extremely low false-alarm probability. In this paper, we propose a fair comparison of robustness and security between modern and classic post-hoc watermarking across various types of classic augmentations and recent sophisticated attacks. Our experiments show that, in a realistic scenario, classic watermarking outperforms modern techniques in terms of security while maintaining robustness. |
| title | Do Modern Post-Hoc Watermarking Methods Beat Broken-Arrows? |
| topic | Cryptography and Security Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.27135 |