Metraipolis › archive › dc_cb5fdf6ed520
SAMP: Self-Adaptive Margin Prioritization For Robust Diffusion Watermarking — arXiv:2611.00069
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.00069
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T10:54:47.232Z
- SHA-256 of the archived text
32b19fe29567b613f058d3c9212f929cd6e74736cb3a134f7f007564d74a4fed- Stable URL of this page
https://metraipolis.com/documento/dc_cb5fdf6ed520
How to cite
SAMP: Self-Adaptive Margin Prioritization For Robust Diffusion Watermarking — arXiv:2611.00069 — arXiv (en), https://arxiv.org/abs/2611.00069 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cb5fdf6ed520 (Metraipolis archive dc_cb5fdf6ed520, sha256 32b19fe29567b613f058d3c9212f929cd6e74736cb3a134f7f007564d74a4fed)
BibTeX
@misc{dccb5fdf6ed520,
title = {SAMP: Self-Adaptive Margin Prioritization For Robust Diffusion Watermarking — arXiv:2611.00069},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.00069},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cb5fdf6ed520; sha256 32b19fe29567b613f058d3c9212f929cd6e74736cb3a134f7f007564d74a4fed},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00069. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Diffusion models have made high-fidelity visual generation widely accessible, while also lowering the barrier to producing convincing visual forgeries and complicating content provenance. Existing watermarking methods typically use a fixed embedding strength throughout denoising or treat all watermark dimensions equally. As a result, they may introduce unnecessary distortion when some watermark dimensions are already reliable, while failing to sufficiently reinforce those that are more vulnerable to subsequent perturbations. Therefore, robust watermarking requires adapting both the embedding strength during denoising and the optimization priority across watermark dimensions. To address this problem, we present SAMP, a self-adaptive framework consisting of global margin regulation and vulnerability-sensitive allocation. Global margin regulation adjusts the embedding strength according to the separation between the target codeword and competing codewords, together with the estimated effects of common attacks. Vulnerability-sensitive allocation identifies watermark dimensions that are more easily weakened by local perturbations and gives them higher optimization priority. Experimental results demonstrate that SAMP achieves an average information recovery accuracy of 0.993. Compared with state-of-the-art methods, SAMP improves PSNR by 16.8% and reduces LPIPS by 47.1%. These results validate the effectiveness of SAMP for reliable and high-quality diffusion watermarking. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI); Multimedia (cs.MM). Pagina del lavoro: https://arxiv.org/abs/2611.00069 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-03T10:49:38.450Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).