Metraipolis › archive › dc_0cca089352eb
What Breaks Local Watermarks? A Robustness Benchmark for Local Invisible Image Watermarking — arXiv:2609.16832
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.16832
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T18:38:40.842Z
- SHA-256 of the archived text
d0901cd33b06f33340d6e873e96369b085853108026b59d36445db6fb6be141c- Stable URL of this page
https://metraipolis.com/documento/dc_0cca089352eb
How to cite
What Breaks Local Watermarks? A Robustness Benchmark for Local Invisible Image Watermarking — arXiv:2609.16832 — arXiv (en), https://arxiv.org/abs/2609.16832 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0cca089352eb (Metraipolis archive dc_0cca089352eb, sha256 d0901cd33b06f33340d6e873e96369b085853108026b59d36445db6fb6be141c)
BibTeX
@misc{dc0cca089352eb,
title = {What Breaks Local Watermarks? A Robustness Benchmark for Local Invisible Image Watermarking — arXiv:2609.16832},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.16832},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0cca089352eb; sha256 d0901cd33b06f33340d6e873e96369b085853108026b59d36445db6fb6be141c},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.16832. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Local image watermarking embeds an invisible signal into selected image regions rather than spreading it across the entire image, enabling payload recovery from specific objects or regions without perceptibly altering the image. Existing studies evaluate the robustness of payload recovery and localization under image transformations, but they often focus on their own proposed method, resulting in narrow evaluations with inconsistent choices of transformations, datasets, and metrics. These inconsistencies across studies limit direct comparisons across methods and muddle the overall picture of local watermark robustness. To address this gap, we present the first systematic robustness benchmark for local watermarks across 55 image transformations, including (i) signal distortions, (ii) changes in image coordinate alignment, (iii) indirect local edits, and (iv) direct watermark edits. The benchmark evaluates MaskWM, WAM, OmniGuard, TrustMark, and PixelSeal, all methods that either provide native localization or require minimal adaptation to support it. Our results show that all evaluated methods are vulnerable to some transformation, with MaskWM standing out as offering the strongest payload recovery and localization, although it has the lowest image quality in the clean setting. Synchronization further improves MaskWM's payload recovery under several geometric transformations, albeit at an additional cost to image quality. A key finding is that local watermark robustness depends strongly on the nature of the transformation: signal distortions are often tolerated by the strongest methods, while geometric misalignment and generative local edits, such as inpainting and outpainting, can completely impair payload recovery. We observe that payload recovery and localization are related but not interchangeable, and both strongly depend on the transformation's impact on the watermark region. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-16 in cs.AI). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI); Cryptography and Security (cs.CR). Pagina del lavoro: https://arxiv.org/abs/2609.16832 — 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 2026-10-15T18:03:09.692Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-16?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).