Metraipolis › archive › dc_8b32ede8f320

Fast segmentation of watermarked texts from large language models through an epidemic change-point framework — arXiv:2509.21160

Source
arXiv (en)
Original
https://arxiv.org/abs/2509.21160
License (as archived)
CC0-1.0
Archived
2026-11-01T02:31:27.096Z
SHA-256 of the archived text
b2b8ceb6e906f3d08b9589a157053b631a1ac4946fd86ff8662d7f31b2cdbe0e
Stable URL of this page
https://metraipolis.com/documento/dc_8b32ede8f320

How to cite

Fast segmentation of watermarked texts from large language models through an epidemic change-point framework — arXiv:2509.21160 — arXiv (en), https://arxiv.org/abs/2509.21160 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8b32ede8f320 (Metraipolis archive dc_8b32ede8f320, sha256 b2b8ceb6e906f3d08b9589a157053b631a1ac4946fd86ff8662d7f31b2cdbe0e)
BibTeX
@misc{dc8b32ede8f320,
  title = {Fast segmentation of watermarked texts from large language models through an epidemic change-point framework — arXiv:2509.21160},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2509.21160},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8b32ede8f320; sha256 b2b8ceb6e906f3d08b9589a157053b631a1ac4946fd86ff8662d7f31b2cdbe0e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2509.21160. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

With the growing use of large language models, concerns over content authenticity have spurred a variety of watermarking schemes. These schemes use secret keys to detect machine-generated text while remaining imperceptible to readers. Detection typically reduces to statistical hypothesis testing for the presence of watermarks, a topic that is now well studied. In contrast, the finer-grained task of localizing which segments of a text are watermarked is much less explored; existing approaches often lack scalability or guarantees robust to paraphrasing and post-editing. We bring a new perspective to this segmentation problem through the lens of epidemic change-points and, by exploiting this connection, propose WISER, a novel and computationally efficient watermark segmentation algorithm. We establish finite-sample error bounds and consistency for detecting multiple watermarked segments in a single text. Complementing these theoretical results, our extensive numerical experiments show that WISER outperforms state-of-the-art baseline methods, both in terms of computational speed as well as accuracy, on various benchmark datasets embedded with diverse watermarking schemes. Together, these theoretical and empirical results position WISER as an effective tool for watermark localization and illustrate how classical statistical ideas can yield theoretically valid and computationally efficient solutions to a modern problem of immediate importance.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv stat.AP, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (stat.ML) ; Machine Learning (cs.LG); Applications (stat.AP); Methodology (stat.ME).
Pagina del lavoro: https://arxiv.org/abs/2509.21160 — 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 2026-11-01T02:13:58.746Z dalla pagina https://arxiv.org/list/stat.AP/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).