Metraipolis › archive › dc_116abd3ffcc1
SpreadMark: Robust Image Watermarking via Spread-Spectrum Embedding — arXiv:2608.03165
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.03165
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-31T12:34:24.439Z
- SHA-256 of the archived text
828ff0189ba35d1fcfbb50160da86536a6b696ff6e2a96a82f9b6b4b2d94c9ee- Stable URL of this page
https://metraipolis.com/documento/dc_116abd3ffcc1
How to cite
SpreadMark: Robust Image Watermarking via Spread-Spectrum Embedding — arXiv:2608.03165 — arXiv (en), https://arxiv.org/abs/2608.03165 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_116abd3ffcc1 (Metraipolis archive dc_116abd3ffcc1, sha256 828ff0189ba35d1fcfbb50160da86536a6b696ff6e2a96a82f9b6b4b2d94c9ee)
BibTeX
@misc{dc116abd3ffcc1,
title = {SpreadMark: Robust Image Watermarking via Spread-Spectrum Embedding — arXiv:2608.03165},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.03165},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_116abd3ffcc1; sha256 828ff0189ba35d1fcfbb50160da86536a6b696ff6e2a96a82f9b6b4b2d94c9ee},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.03165. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Invisible image watermarks are increasingly used for deepfake detection and provenance tracking, where they must survive not only incidental distortions but also deliberate removal. We revisit spread-spectrum embedding, a classical watermarking principle, inside a modern neural post-hoc watermarking architecture. Our starting point is a measurement: in existing encoder-decoder schemes each message bit occupies only a small fraction of the image, a shared contributing factor to their fragility, since removal then need only disturb the region a bit occupies. SpreadMark instead spreads each bit as a dense pseudo-random codeword over the whole image and recovers it by matched-filtering a learned cover-suppressed chip representation, with a parallel convolutional decoding path and sparsification-aware training. A conditional chip-space analysis shows that, under a codeword-independent perturbation model, dense spreading increases the budget required to disrupt matched-filter recovery. Evaluated on COCO and DIV2K against nine schemes, SpreadMark is the only evaluated method retaining high detection under both the regeneration and the latent-space sparsification settings we test, with competitive JPEG and additive-noise robustness. It keeps the embedded watermark imperceptible, maintaining high perceptual quality on both COCO and DIV2K. Tema degli esploratori: fiducia digitale e crittografia (retro-catalogo arXiv: annunci del 2026-08-05 in cs.CR). Categorie arXiv: Cryptography and Security (cs.CR) ; Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2608.03165 — 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 2026-10-31T12:21:50.555Z dalla pagina https://arxiv.org/catchup/cs.CR/2026-08-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).