Metraipolis › archive › dc_e6fc079fbe4d

DenMark: Robust Semantic Watermarking for Diffusion Language Models — arXiv:2609.14257

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.14257
License (as archived)
CC0-1.0
Archived
2026-10-15T23:15:05.795Z
SHA-256 of the archived text
a53953979741752b545df02bb77728cf215b51d5ac5d2fa476f91a846c9140af
Stable URL of this page
https://metraipolis.com/documento/dc_e6fc079fbe4d

How to cite

DenMark: Robust Semantic Watermarking for Diffusion Language Models — arXiv:2609.14257 — arXiv (en), https://arxiv.org/abs/2609.14257 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e6fc079fbe4d (Metraipolis archive dc_e6fc079fbe4d, sha256 a53953979741752b545df02bb77728cf215b51d5ac5d2fa476f91a846c9140af)
BibTeX
@misc{dce6fc079fbe4d,
  title = {DenMark: Robust Semantic Watermarking for Diffusion Language Models — arXiv:2609.14257},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.14257},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e6fc079fbe4d; sha256 a53953979741752b545df02bb77728cf215b51d5ac5d2fa476f91a846c9140af},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.14257. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Semantic text watermarks encode signals in meaning rather than surface token choices, offering robustness to paraphrasing and other semantic-preserving edits. Existing semantic watermarking methods are primarily designed for autoregressive language models (ARLMs), where completed candidate units can be generated and scored before generation proceeds. This paradigm does not naturally extend to diffusion language models (DLMs), where semantic units remain incomplete during intermediate denoising steps and tokens may be updated in flexible orders. We propose DenMark, a semantic watermarking framework that injects key-dependent signals directly into the DLM denoising process. DenMark partitions the output into fixed token regions and uses temporary rollouts as semantic lookahead: conditional completions estimate the eventual semantics of an incomplete region, enabling DenMark to select local updates with higher estimated semantic watermark scores. Repeating this procedure across denoising steps progressively accumulates watermark evidence in the final output. For detection, DenMark uses calibrated scanning over candidate unit sizes to remain robust to boundary shifts introduced by semantic attacks. Across four DLMs, three datasets, and four semantic attacks, DenMark gives the strongest overall robustness and achieves the best TPR at each reported operating point in 46 of the 48 backbone-dataset-attack combinations. Overall, DenMark provides an effective semantic watermark for DLMs. Code is available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-15 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2609.14257 — 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 2026-10-15T22:51:09.873Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).