Metraipolis › archive › dc_074fa5a98fe1
Watermarking: from Impossibility to Auditable Compliance — arXiv:2610.06317
- Source
- arXiv
- Original
- https://arxiv.org/abs/2610.06317
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T05:29:58.010Z
- SHA-256 of the archived text
19fdfad7ca4652d3258416e837fe32736d8085ab7160475afdd12a944c83d1bd- Stable URL of this page
https://metraipolis.com/documento/dc_074fa5a98fe1
How to cite
Watermarking: from Impossibility to Auditable Compliance — arXiv:2610.06317 — arXiv, https://arxiv.org/abs/2610.06317 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_074fa5a98fe1 (Metraipolis archive dc_074fa5a98fe1, sha256 19fdfad7ca4652d3258416e837fe32736d8085ab7160475afdd12a944c83d1bd)
BibTeX
@misc{dc074fa5a98fe1,
title = {Watermarking: from Impossibility to Auditable Compliance — arXiv:2610.06317},
howpublished = {arXiv},
url = {https://arxiv.org/abs/2610.06317},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_074fa5a98fe1; sha256 19fdfad7ca4652d3258416e837fe32736d8085ab7160475afdd12a944c83d1bd},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.06317. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Article 50 (2) of the EU Artificial Intelligence Act requires providers of generative systems to make synthetic outputs machine-readable and detectable, while qualifying the effectiveness, interoperability, robustness, and reliability by technical feasibility, cost, content-specific limits, and the state of the art. For free-form text, one important implementation route is the implementation of a generative watermarking procedure, which poses a compliance problem that is hard to address. Strong watermarking is impossible against adaptive removal, while ordinary edits attenuate statistical evidence, and unmarked human text may overlap distributionally with machine output. This article develops an auditable alternative. First, it defines a description-length robustness profile. A finite-sample bound shows that detectable bias decays and that the required sample size grows with the inverse square of the decay rate. This replaces an unidentified Shannon-entropy constant with collision entropy. Second, it constructs label-conditional conformal prediction sets with separate false-attribution and false-exclusion levels, reporting ``watermark supported,'' ``not supported,'' or ``inconclusive''. Coverage is obtained as a finite-sample result and is class-conditional under exchangeability. A small reproducible simulation of a tournament watermark confirms both claims and shows that the surviving-token rule overstates the tolerable edit rate roughly twofold. The resulting premarket certificate, signed detector report, and postmarket recalibration protocol operationalize the Commission's 2026 Code of Practice without claiming universal robustness. Tema degli esploratori: fiducia digitale e crittografia (elenco arXiv cs.CR, nuovi lavori del giorno). Categorie arXiv: Cryptography and Security (cs.CR) ; Machine Learning (cs.LG); Machine Learning (stat.ML). Pagina del lavoro: https://arxiv.org/abs/2610.06317 — 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 2026-10-06T05:26:35.372Z dalla pagina https://arxiv.org/list/cs.CR/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).