Saved in:
Bibliographic Details
Main Authors: Li, Wangjie, Li, Lin, Hong, Qingyang
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.19974
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914170182565888
author Li, Wangjie
Li, Lin
Hong, Qingyang
author_facet Li, Wangjie
Li, Lin
Hong, Qingyang
contents The rapid advancement of speech synthesis and voice conversion technologies has raised significant security concerns in multimedia forensics. Although current detection models demonstrate impressive performance, they struggle to maintain effectiveness against constantly evolving deepfake attacks. Additionally, continually fine-tuning these models using historical training data incurs substantial computational and storage costs. To address these limitations, we propose a novel framework that incorporates Universal Adversarial Perturbation (UAP) into audio deepfake detection, enabling models to retain knowledge of historical spoofing distribution without direct access to past data. Our method integrates UAP seamlessly with pre-trained self-supervised audio models during fine-tuning. Extensive experiments validate the effectiveness of our approach, showcasing its potential as an efficient solution for continual learning in audio deepfake detection.
format Preprint
id arxiv_https___arxiv_org_abs_2511_19974
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Continual Audio Deepfake Detection via Universal Adversarial Perturbation
Li, Wangjie
Li, Lin
Hong, Qingyang
Sound
The rapid advancement of speech synthesis and voice conversion technologies has raised significant security concerns in multimedia forensics. Although current detection models demonstrate impressive performance, they struggle to maintain effectiveness against constantly evolving deepfake attacks. Additionally, continually fine-tuning these models using historical training data incurs substantial computational and storage costs. To address these limitations, we propose a novel framework that incorporates Universal Adversarial Perturbation (UAP) into audio deepfake detection, enabling models to retain knowledge of historical spoofing distribution without direct access to past data. Our method integrates UAP seamlessly with pre-trained self-supervised audio models during fine-tuning. Extensive experiments validate the effectiveness of our approach, showcasing its potential as an efficient solution for continual learning in audio deepfake detection.
title Continual Audio Deepfake Detection via Universal Adversarial Perturbation
topic Sound
url https://arxiv.org/abs/2511.19974