Metraipolis › archive › dc_fad9642de02f
MARC: Multi-Bit Watermarking for Autoregressive Audio Generation against Codec Attacks — arXiv:2610.11488
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.11488
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-09T06:20:27.613Z
- SHA-256 of the archived text
9a2b1c637852907795a1207318116d62a9b138018092bbf20a4bd49719d53f80- Stable URL of this page
https://metraipolis.com/documento/dc_fad9642de02f
How to cite
MARC: Multi-Bit Watermarking for Autoregressive Audio Generation against Codec Attacks — arXiv:2610.11488 — arXiv (en), https://arxiv.org/abs/2610.11488 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fad9642de02f (Metraipolis archive dc_fad9642de02f, sha256 9a2b1c637852907795a1207318116d62a9b138018092bbf20a4bd49719d53f80)
BibTeX
@misc{dcfad9642de02f,
title = {MARC: Multi-Bit Watermarking for Autoregressive Audio Generation against Codec Attacks — arXiv:2610.11488},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.11488},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fad9642de02f; sha256 9a2b1c637852907795a1207318116d62a9b138018092bbf20a4bd49719d53f80},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.11488. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Generated audio is now used in a range of applications, creating a need to verify its origin after distribution and signal processing. This task is particularly challenging for autoregressive audio generation because codec processing can alter the token sequence recovered from the waveform. Such changes reduce the reliability of watermark detection and payload decoding. Existing methods construct token groups using either intrinsic token representations or substitution patterns caused by transformations. As a result, intrinsic token relationships and codec induced substitutions are modeled separately. In addition, most methods support only zero bit detection. They can determine whether a watermark is present but cannot distinguish individual generated outputs. We propose \textbf{MARC}, a multi-bit generative watermarking method for autoregressive audio generation. MARC integrates intrinsic token representations with confusion patterns obtained through retokenization and multiple codecs, forming a codec-aware token-cluster space. Within this space, payload-driven cluster scheduling is used to embed a multi-bit watermark, while detection and payload decoding are performed on retokenized observations. Experiments on speech, dialogue, and music generation show that MARC achieves an average of 97.3\% bit extraction accuracy on unmodified watermarked audio and the watermark can still be extracted under diverse codec attacks. MARC also demonstrates robustness to overwriting attacks.
Tema degli esploratori: fiducia digitale e crittografia (elenco arXiv cs.CR, nuovi lavori del giorno).
Categorie arXiv: Cryptography and Security (cs.CR).
Pagina del lavoro: https://arxiv.org/abs/2610.11488 — 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 2026-10-09T05:50:00.892Z dalla pagina https://arxiv.org/list/cs.CR/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).