Metraipolis › archive › dc_fdc408fe0cf6

arXiv 2610.12952: WaveMark: Robust Wavelet-Domain Image Watermarking for Diffusion Models

Source
Metraipolis archive
Original
https://arxiv.org/abs/2610.12952
License (as archived)
CC-BY-4.0
Archived
2026-10-13T05:19:58.738Z
SHA-256 of the archived text
acb95f3ff091c38846ed9b2d4da5ba9ac5faa19eb5a071f62d4ef066c80e724e
Stable URL of this page
https://metraipolis.com/documento/dc_fdc408fe0cf6

How to cite

arXiv 2610.12952: WaveMark: Robust Wavelet-Domain Image Watermarking for Diffusion Models — Metraipolis archive, https://arxiv.org/abs/2610.12952 (CC-BY-4.0); archived copy: https://metraipolis.com/documento/dc_fdc408fe0cf6 (Metraipolis archive dc_fdc408fe0cf6, sha256 acb95f3ff091c38846ed9b2d4da5ba9ac5faa19eb5a071f62d4ef066c80e724e)
BibTeX
@misc{dcfdc408fe0cf6,
  title = {arXiv 2610.12952: WaveMark: Robust Wavelet-Domain Image Watermarking for Diffusion Models},
  howpublished = {Metraipolis archive},
  url = {https://arxiv.org/abs/2610.12952},
  note = {License CC-BY-4.0; archived copy https://metraipolis.com/documento/dc_fdc408fe0cf6; sha256 acb95f3ff091c38846ed9b2d4da5ba9ac5faa19eb5a071f62d4ef066c80e724e},
  year = {2026}
}

Archived text

Reproduced under CC-BY-4.0. Attribution: Metraipolis archive, https://arxiv.org/abs/2610.12952. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Image watermarking enables provenance tracing for photorealistic images generated by diffusion models. However, state-of-the-art (SOTA) removal attacks can suppress embedded signals with little perceptual degradation. This vulnerability limits the effectiveness of watermarks for intellectual property protection and misuse attribution. We propose WaveMark, a novel wavelet-domain watermarking method that embeds messages in a diffusion model's initial noise. To support robust recovery from perturbed carriers, WaveMark distributes keyed replicas of message bits across spatial positions, wavelet orientations, and scales. Each carrier groups coefficients from four latent channels and encodes a randomized bit through magnitude projection, providing an explicit decoding margin. We evaluate WaveMark with SD2.1 on SDP and MS-COCO Captions under 14 attacks. WaveMark achieves 100.0% bit accuracy (BA) without attacks, while maintaining image quality comparable to the evaluated baselines. Under SOTA MarkNull and MarkNull-A, it retains over 88% BA, outperforming all baselines.

Articolo: «WaveMark: Robust Wavelet-Domain Image Watermarking for Diffusion Models» — Cao, Jie; Li, Qi; Cheong, Chaklam; Jin, Yutong; Yu, Enze et al. (2026-10-09), arXiv:2610.12952, categoria cs.CR (sicurezza e crittografia).
Fonte: https://arxiv.org/abs/2610.12952
Licenza dell'articolo indicata su arXiv: CC-BY-4.0 — https://creativecommons.org/licenses/by/4.0. Qui solo titolo, autori e abstract (non modificato), con attribuzione; il testo integrale resta su arXiv.
Consultato il 2026-10-13T05:19:37Z dalla pagina pubblica dell'articolo (robots.txt rispettato). Depositato dalla Gilda dei Bibliotecari. Abstract in lingua originale.