Metraipolis › archive › dc_629e7dbf588b
SimpleMark: Fast Multi-Bit Text Watermarking under f -Divergence Constraints — arXiv:2610.05712
- Source
- arXiv
- Original
- https://arxiv.org/abs/2610.05712
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T05:27:07.374Z
- SHA-256 of the archived text
5b358273048c8c17a33d2b839994a3ff61bdcb29fe1e174e79cca1046949d1a8- Stable URL of this page
https://metraipolis.com/documento/dc_629e7dbf588b
How to cite
SimpleMark: Fast Multi-Bit Text Watermarking under f -Divergence Constraints — arXiv:2610.05712 — arXiv, https://arxiv.org/abs/2610.05712 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_629e7dbf588b (Metraipolis archive dc_629e7dbf588b, sha256 5b358273048c8c17a33d2b839994a3ff61bdcb29fe1e174e79cca1046949d1a8)
BibTeX
@misc{dc629e7dbf588b,
title = {SimpleMark: Fast Multi-Bit Text Watermarking under f -Divergence Constraints — arXiv:2610.05712},
howpublished = {arXiv},
url = {https://arxiv.org/abs/2610.05712},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_629e7dbf588b; sha256 5b358273048c8c17a33d2b839994a3ff61bdcb29fe1e174e79cca1046949d1a8},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.05712. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We introduce a framework for multi-bit text watermarking with security defined directly through $f$-divergence from the base language model distribution. Unlike prior approaches that focus on average-key distortion-freeness or a particular statistical distance, our formulation supports general $f$-divergences, including total variation and KL divergence, and enforces the guarantee for each realized key and embedded message. We develop a coding-based watermarking scheme that optimally biases next-token distributions subject to a prescribed divergence budget, and characterize the resulting tradeoff between embedding rate, decoding reliability, and statistical security. Experimentally, we compare our method against prior multi-bit watermarking schemes across modern language models and payload regimes. Our approach achieves substantially lower watermark detectability while maintaining competitive message-recovery performance and generation quality. Our results provide a unified view of secure multi-bit watermarking and recover several commonly used security notions as special cases. 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); Information Theory (cs.IT). Pagina del lavoro: https://arxiv.org/abs/2610.05712 — 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 2026-10-06T05:24:06.063Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).