@inproceedings{yue-etal-2026-tts,
title = "{TTS}-Guard: Black-Box Ownership Verification of Text-to-Speech Models via Adaptive Adversarial Speaker-Pair Fingerprints",
author = "Yue, Xubin and
Xu, Zhenhua and
Wang, Zhebo and
Li, Mengting and
Zhou, Zijie and
Xing, Wenpeng and
Kong, Dezhang and
Han, Meng",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.236/",
pages = "4958--4973",
ISBN = "979-8-89176-462-0",
abstract = "The rapid maturation of zero-shot Text-to-Speech (TTS) models has turned high-quality voice cloning into a widely available capability, raising acute concerns over unauthorised replication, fine-tuning and resale of proprietary speech models. Yet ownership verification for TTS remains largely open: speech is a continuous waveform whose perturbations are easily destroyed by routine signal processing, and the human auditory system imposes a much tighter perceptual budget than vision. We present \textbf{TTS-Guard}, a black-box ownership verification framework for TTS models built on \textit{adversarial speaker-pair fingerprints}. TTS-Guard(i) selects key speaker pairs in a \textit{dual} embedding space for architecture-agnostic stealth;(ii) optimises a perturbation through an \textit{adaptive curriculum} of shadow models covering fine-tuning, pruning, quantisation and distillation; and (iii) aggregates black-box queries into a calibrated \textit{Verification Confidence Score}. On five mainstream TTS systems, TTS-Guard reaches an average Fingerprint Success Rate of 96.4{\%} at a False Positive Rate of 5.8{\%}, while preserving intelligibility and naturalness. The fingerprint remains effective against ten audio attacks, six model modifications, and two state-of-the-art adversarial purifiers."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yue-etal-2026-tts">
<titleInfo>
<title>TTS-Guard: Black-Box Ownership Verification of Text-to-Speech Models via Adaptive Adversarial Speaker-Pair Fingerprints</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xubin</namePart>
<namePart type="family">Yue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhenhua</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhebo</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mengting</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zijie</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenpeng</namePart>
<namePart type="family">Xing</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dezhang</namePart>
<namePart type="family">Kong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Meng</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>The rapid maturation of zero-shot Text-to-Speech (TTS) models has turned high-quality voice cloning into a widely available capability, raising acute concerns over unauthorised replication, fine-tuning and resale of proprietary speech models. Yet ownership verification for TTS remains largely open: speech is a continuous waveform whose perturbations are easily destroyed by routine signal processing, and the human auditory system imposes a much tighter perceptual budget than vision. We present TTS-Guard, a black-box ownership verification framework for TTS models built on adversarial speaker-pair fingerprints. TTS-Guard(i) selects key speaker pairs in a dual embedding space for architecture-agnostic stealth;(ii) optimises a perturbation through an adaptive curriculum of shadow models covering fine-tuning, pruning, quantisation and distillation; and (iii) aggregates black-box queries into a calibrated Verification Confidence Score. On five mainstream TTS systems, TTS-Guard reaches an average Fingerprint Success Rate of 96.4% at a False Positive Rate of 5.8%, while preserving intelligibility and naturalness. The fingerprint remains effective against ten audio attacks, six model modifications, and two state-of-the-art adversarial purifiers.</abstract>
<identifier type="citekey">yue-etal-2026-tts</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.236/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>4958</start>
<end>4973</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TTS-Guard: Black-Box Ownership Verification of Text-to-Speech Models via Adaptive Adversarial Speaker-Pair Fingerprints
%A Yue, Xubin
%A Xu, Zhenhua
%A Wang, Zhebo
%A Li, Mengting
%A Zhou, Zijie
%A Xing, Wenpeng
%A Kong, Dezhang
%A Han, Meng
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F yue-etal-2026-tts
%X The rapid maturation of zero-shot Text-to-Speech (TTS) models has turned high-quality voice cloning into a widely available capability, raising acute concerns over unauthorised replication, fine-tuning and resale of proprietary speech models. Yet ownership verification for TTS remains largely open: speech is a continuous waveform whose perturbations are easily destroyed by routine signal processing, and the human auditory system imposes a much tighter perceptual budget than vision. We present TTS-Guard, a black-box ownership verification framework for TTS models built on adversarial speaker-pair fingerprints. TTS-Guard(i) selects key speaker pairs in a dual embedding space for architecture-agnostic stealth;(ii) optimises a perturbation through an adaptive curriculum of shadow models covering fine-tuning, pruning, quantisation and distillation; and (iii) aggregates black-box queries into a calibrated Verification Confidence Score. On five mainstream TTS systems, TTS-Guard reaches an average Fingerprint Success Rate of 96.4% at a False Positive Rate of 5.8%, while preserving intelligibility and naturalness. The fingerprint remains effective against ten audio attacks, six model modifications, and two state-of-the-art adversarial purifiers.
%U https://aclanthology.org/2026.findings-emnlp.236/
%P 4958-4973
Markdown (Informal)
[TTS-Guard: Black-Box Ownership Verification of Text-to-Speech Models via Adaptive Adversarial Speaker-Pair Fingerprints](https://aclanthology.org/2026.findings-emnlp.236/) (Yue et al., Findings 2026)
ACL
- Xubin Yue, Zhenhua Xu, Zhebo Wang, Mengting Li, Zijie Zhou, Wenpeng Xing, Dezhang Kong, and Meng Han. 2026. TTS-Guard: Black-Box Ownership Verification of Text-to-Speech Models via Adaptive Adversarial Speaker-Pair Fingerprints. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 4958–4973, Budapest, Hungary. Association for Computational Linguistics.