AudioMarkBench: Benchmarking Robustness of Audio Watermarking

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Liu, Hongbin, Guo, Moyang, Jiang, Zhengyuan, Wang, Lun, Gong, Neil Zhenqiang
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866913577027239936
author Liu, Hongbin
Guo, Moyang
Jiang, Zhengyuan
Wang, Lun
Gong, Neil Zhenqiang
author_facet Liu, Hongbin
Guo, Moyang
Jiang, Zhengyuan
Wang, Lun
Gong, Neil Zhenqiang
contents The increasing realism of synthetic speech, driven by advancements in text-to-speech models, raises ethical concerns regarding impersonation and disinformation. Audio watermarking offers a promising solution via embedding human-imperceptible watermarks into AI-generated audios. However, the robustness of audio watermarking against common/adversarial perturbations remains understudied. We present AudioMarkBench, the first systematic benchmark for evaluating the robustness of audio watermarking against watermark removal and watermark forgery. AudioMarkBench includes a new dataset created from Common-Voice across languages, biological sexes, and ages, 3 state-of-the-art watermarking methods, and 15 types of perturbations. We benchmark the robustness of these methods against the perturbations in no-box, black-box, and white-box settings. Our findings highlight the vulnerabilities of current watermarking techniques and emphasize the need for more robust and fair audio watermarking solutions. Our dataset and code are publicly available at https://github.com/moyangkuo/AudioMarkBench.
format Preprint
id arxiv_https___arxiv_org_abs_2406_06979
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle AudioMarkBench: Benchmarking Robustness of Audio Watermarking
Liu, Hongbin
Guo, Moyang
Jiang, Zhengyuan
Wang, Lun
Gong, Neil Zhenqiang
Machine Learning
Cryptography and Security
Sound
Audio and Speech Processing
The increasing realism of synthetic speech, driven by advancements in text-to-speech models, raises ethical concerns regarding impersonation and disinformation. Audio watermarking offers a promising solution via embedding human-imperceptible watermarks into AI-generated audios. However, the robustness of audio watermarking against common/adversarial perturbations remains understudied. We present AudioMarkBench, the first systematic benchmark for evaluating the robustness of audio watermarking against watermark removal and watermark forgery. AudioMarkBench includes a new dataset created from Common-Voice across languages, biological sexes, and ages, 3 state-of-the-art watermarking methods, and 15 types of perturbations. We benchmark the robustness of these methods against the perturbations in no-box, black-box, and white-box settings. Our findings highlight the vulnerabilities of current watermarking techniques and emphasize the need for more robust and fair audio watermarking solutions. Our dataset and code are publicly available at https://github.com/moyangkuo/AudioMarkBench.
title AudioMarkBench: Benchmarking Robustness of Audio Watermarking
topic Machine Learning
Cryptography and Security
Sound
Audio and Speech Processing
url https://arxiv.org/abs/2406.06979