GROOT: Generating Robust Watermark for Diffusion-Model-Based Audio Synthesis

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Weizhi, Li, Yue, Lin, Dongdong, Tian, Hui, Li, Haizhou
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910530400157696
author Liu, Weizhi
Li, Yue
Lin, Dongdong
Tian, Hui
Li, Haizhou
author_facet Liu, Weizhi
Li, Yue
Lin, Dongdong
Tian, Hui
Li, Haizhou
contents Amid the burgeoning development of generative models like diffusion models, the task of differentiating synthesized audio from its natural counterpart grows more daunting. Deepfake detection offers a viable solution to combat this challenge. Yet, this defensive measure unintentionally fuels the continued refinement of generative models. Watermarking emerges as a proactive and sustainable tactic, preemptively regulating the creation and dissemination of synthesized content. Thus, this paper, as a pioneer, proposes the generative robust audio watermarking method (Groot), presenting a paradigm for proactively supervising the synthesized audio and its source diffusion models. In this paradigm, the processes of watermark generation and audio synthesis occur simultaneously, facilitated by parameter-fixed diffusion models equipped with a dedicated encoder. The watermark embedded within the audio can subsequently be retrieved by a lightweight decoder. The experimental results highlight Groot's outstanding performance, particularly in terms of robustness, surpassing that of the leading state-of-the-art methods. Beyond its impressive resilience against individual post-processing attacks, Groot exhibits exceptional robustness when facing compound attacks, maintaining an average watermark extraction accuracy of around 95%.
format Preprint
id arxiv_https___arxiv_org_abs_2407_10471
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle GROOT: Generating Robust Watermark for Diffusion-Model-Based Audio Synthesis
Liu, Weizhi
Li, Yue
Lin, Dongdong
Tian, Hui
Li, Haizhou
Cryptography and Security
Artificial Intelligence
Sound
Audio and Speech Processing
Amid the burgeoning development of generative models like diffusion models, the task of differentiating synthesized audio from its natural counterpart grows more daunting. Deepfake detection offers a viable solution to combat this challenge. Yet, this defensive measure unintentionally fuels the continued refinement of generative models. Watermarking emerges as a proactive and sustainable tactic, preemptively regulating the creation and dissemination of synthesized content. Thus, this paper, as a pioneer, proposes the generative robust audio watermarking method (Groot), presenting a paradigm for proactively supervising the synthesized audio and its source diffusion models. In this paradigm, the processes of watermark generation and audio synthesis occur simultaneously, facilitated by parameter-fixed diffusion models equipped with a dedicated encoder. The watermark embedded within the audio can subsequently be retrieved by a lightweight decoder. The experimental results highlight Groot's outstanding performance, particularly in terms of robustness, surpassing that of the leading state-of-the-art methods. Beyond its impressive resilience against individual post-processing attacks, Groot exhibits exceptional robustness when facing compound attacks, maintaining an average watermark extraction accuracy of around 95%.
title GROOT: Generating Robust Watermark for Diffusion-Model-Based Audio Synthesis
topic Cryptography and Security
Artificial Intelligence
Sound
Audio and Speech Processing
url https://arxiv.org/abs/2407.10471