Metraipolis › archive › dc_2891cae947cb

ScrambleMark: Zero-Query Watermark-Agnostic Black-Box Evasion of Modern Speech Watermarking — arXiv:2611.04122

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.04122
License (as archived)
CC0-1.0
Archived
2026-11-04T12:38:45.813Z
SHA-256 of the archived text
ce9113f3ddd0fe77c2b94d7cfc91c034bcd8b66a1a50a12a2a5f48e46cc5923f
Stable URL of this page
https://metraipolis.com/documento/dc_2891cae947cb

How to cite

ScrambleMark: Zero-Query Watermark-Agnostic Black-Box Evasion of Modern Speech Watermarking — arXiv:2611.04122 — arXiv (en), https://arxiv.org/abs/2611.04122 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2891cae947cb (Metraipolis archive dc_2891cae947cb, sha256 ce9113f3ddd0fe77c2b94d7cfc91c034bcd8b66a1a50a12a2a5f48e46cc5923f)
BibTeX
@misc{dc2891cae947cb,
  title = {ScrambleMark: Zero-Query Watermark-Agnostic Black-Box Evasion of Modern Speech Watermarking — arXiv:2611.04122},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.04122},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2891cae947cb; sha256 ce9113f3ddd0fe77c2b94d7cfc91c034bcd8b66a1a50a12a2a5f48e46cc5923f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04122. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Speech watermarking is becoming a key defense for digital copyright and content authentication. Existing attacks treat evasion as a removal problem: they erase the watermark, relying on detector access or on speech data that is hard to collect, such as paired clean-watermarked or clean target speaker speech. Commercial platforms are moving to close off these assumptions. TrustedAudio, for instance, restricts detection to authenticated users and denies meaningful detection feedback to unauthorized parties. Adversaries thus cannot tell whether a sample is watermarked or which watermark it carries, nor reliably remove it without degrading speech quality. In this work, we show that evading a speech watermark does not require erasing it: detection relies on the structural consistency of the embedded pattern, and disrupting this consistency is enough to defeat it. Building on this observation, we identify harmonic structure as an effective attack surface, as perturbing it breaks watermark consistency while preserving perceptual quality. We therefore propose ScrambleMark, a zero-query, watermark-agnostic, black-box attack that evades detection through harmonic scrambling. ScrambleMark combines a deterministic engine for discovering transferable harmonic perturbations with a generative model that learns randomized scrambling patterns, avoiding reliance on fixed attack rules. Across three commercial platforms (Google SynthID, Resemble AI, and TrustedAudio), ScrambleMark is the only attack to both evade detection and keep speech natural, achieving nearly 97% evasion and a 4.2/5 human rating, far above the 1.1 to 1.7 of prior attacks. Beyond evasion, ScrambleMark withstands adaptive recovery designed to reverse it, evidence that structural evasion is hard to mitigate in practice.

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).
Pagina del lavoro: https://arxiv.org/abs/2611.04122 — 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 2026-11-04T12:29:17.133Z dalla pagina https://arxiv.org/list/cs.CR/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).