Continual Unsupervised Domain Adaptation for Audio Deepfake Detection

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F26%3A0199990" target="_blank" >RIV/00216305:26230/26:0199990 - isvavai.cz</a>

Výsledek na webu

<a href="https://ieeexplore.ieee.org/document/10890538" target="_blank" >https://ieeexplore.ieee.org/document/10890538</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/ICASSP49660.2025.10890538" target="_blank" >10.1109/ICASSP49660.2025.10890538</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Continual Unsupervised Domain Adaptation for Audio Deepfake Detection

Popis výsledku v původním jazyce

Audio deepfake detection (ADD) aims to verify the authenticity of audio. However, its performance declines sharply when facing significant domain discrepancies caused by unknown datasets. Unsupervised domain adaptation (UDA) has been applied to mitigate domain mismatch. However, as generative models evolve, existing UDA methods struggle with catastrophic forgetting when facing continuously emerging spoofing methods. To address this challenge, we introduce continual UDA for ADD, which involves sequentially training across multiple target domains with continual learning. We propose a causality-distillation-based continual domain adversarial training framework for continual UDA, called CD-DAT. Specifically, we employ the domain adversarial training (DAT) framework to learn both spoofing-discriminative and domain-invariant deep features. In addition, we design a continual learning algorithm utilizing causality distillation to capture the mapping between utterances and classes, effectively mitigating forgetting and maintaining generalization. Experiments demonstrated that CD-DAT improved detection performance across all domains, confirming its memory stability and learning plasticity.

Název v anglickém jazyce

Continual Unsupervised Domain Adaptation for Audio Deepfake Detection

Popis výsledku anglicky

Audio deepfake detection (ADD) aims to verify the authenticity of audio. However, its performance declines sharply when facing significant domain discrepancies caused by unknown datasets. Unsupervised domain adaptation (UDA) has been applied to mitigate domain mismatch. However, as generative models evolve, existing UDA methods struggle with catastrophic forgetting when facing continuously emerging spoofing methods. To address this challenge, we introduce continual UDA for ADD, which involves sequentially training across multiple target domains with continual learning. We propose a causality-distillation-based continual domain adversarial training framework for continual UDA, called CD-DAT. Specifically, we employ the domain adversarial training (DAT) framework to learn both spoofing-discriminative and domain-invariant deep features. In addition, we design a continual learning algorithm utilizing causality distillation to capture the mapping between utterances and classes, effectively mitigating forgetting and maintaining generalization. Experiments demonstrated that CD-DAT improved detection performance across all domains, confirming its memory stability and learning plasticity.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2025

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Proceedings - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing

ISBN

979-8-3503-6874-1

ISSN

—

e-ISSN

—

Počet stran výsledku

5

Strana od-do

—

Název nakladatele

Institute of Electrical and Electronics Engineers Inc.

Místo vydání

Hyderabad, Indická republika

Místo konání akce

Hyderabad, Indická republika

Datum konání akce

6. 4. 2025

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—