Metraipolis › archive › dc_72672ef92021

Diffusion-Generated Image Watermarking: A Two-Axis Taxonomy and Three Protocol-Bounded Case Studies — arXiv:2610.09755

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.09755
License (as archived): CC0-1.0
Archived: 2026-10-08T12:47:34.240Z
SHA-256 of the archived text: 61339fdd6f68e5837ccb4e33787eb07175d5ed0729ba1745762bd24bc4e5c0c3
Stable URL of this page: https://metraipolis.com/documento/dc_72672ef92021

How to cite

Diffusion-Generated Image Watermarking: A Two-Axis Taxonomy and Three Protocol-Bounded Case Studies — arXiv:2610.09755 — arXiv (en), https://arxiv.org/abs/2610.09755 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_72672ef92021 (Metraipolis archive dc_72672ef92021, sha256 61339fdd6f68e5837ccb4e33787eb07175d5ed0729ba1745762bd24bc4e5c0c3)

BibTeX

@misc{dc72672ef92021,
  title = {Diffusion-Generated Image Watermarking: A Two-Axis Taxonomy and Three Protocol-Bounded Case Studies — arXiv:2610.09755},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.09755},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_72672ef92021; sha256 61339fdd6f68e5837ccb4e33787eb07175d5ed0729ba1745762bd24bc4e5c0c3},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.09755. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Watermarking diffusion-generated images requires balancing provenance signals with image quality, robustness, and computational cost. This work organizes methods along two axes: insertion mechanism and primary signal-bearing representation, and formalizes a representative $z_T$-Fourier pipeline for verification and identification. We then use the taxonomy to structure three protocol-bounded case studies. The first examines associations among frequency integrity, detection, quality, and cropping behavior. The second revisits persistence under seed-linked and seed-independent editing and formulates a scoped Semantic Imprinting Hypothesis without claiming a localized carrier or causal mechanism. The third studies single-shot VAE-latent phase modulation, including its efficiency, regeneration robustness, and robustness--quality operating points. Finally, we separate four content-level attack families from model/pipeline adaptation, propose corresponding evaluation protocols and testable conjectures for parameter-tuning threats, and identify additional temporal extensions for video. These analyses do not establish a universal ranking; instead, they provide a framework for matched, protocol-aware comparisons of watermarking systems for diffusion-generated images.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.09755 — 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 2026-10-08T12:18:15.408Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).