Metraipolis › archive › dc_8bbaa776caab

Query-efficient scan-and-search watermark localization — arXiv:2611.02030

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.02030
License (as archived)
CC0-1.0
Archived
2026-11-03T10:36:21.682Z
SHA-256 of the archived text
198a7dcff1e6b132af49969b818488e588ceaf23bd402719fa34dcc712384a76
Stable URL of this page
https://metraipolis.com/documento/dc_8bbaa776caab

How to cite

Query-efficient scan-and-search watermark localization — arXiv:2611.02030 — arXiv (en), https://arxiv.org/abs/2611.02030 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8bbaa776caab (Metraipolis archive dc_8bbaa776caab, sha256 198a7dcff1e6b132af49969b818488e588ceaf23bd402719fa34dcc712384a76)
BibTeX
@misc{dc8bbaa776caab,
  title = {Query-efficient scan-and-search watermark localization — arXiv:2611.02030},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.02030},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8bbaa776caab; sha256 198a7dcff1e6b132af49969b818488e588ceaf23bd402719fa34dcc712384a76},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.02030. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Recently, the detection of AI-generated content has been of particular importance in various fields of our society. For accountability purposes, many large language models (LLMs) have implicitly watermarked their outputs. Localizing such watermarks requires a piece of text to undergo an additional verification process. Existing localization methods typically rely on dense token-level scoring, making verification costly even when an LLM-generated watermark only sparsely appears. To tackle this problem, we design a new adaptive allocation strategy that first maintains broad document coverage and then progressively concentrates the detection budget on regions that exhibit stronger watermark evidence or are more likely to contain watermarked content. We then transform the statistical signals from the selected regions into e-values and employ the proposed token-weighted e-BH procedure to determine the localized watermark regions. The resulting framework is called BELL (Budgeted E-evidence Localization for LLM Watermarks). Theoretically, BELL can control the token-weighted false discovery rate (FDR) without independence assumptions across regions. Finally, extensive experimental results demonstrate that BELL consistently outperforms competing methods across multiple LLMs, datasets, and watermarking schemes.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.02030 — 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 2026-11-03T10:29:48.835Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).