AudioMarkBench: Benchmarking Robustness of Audio Watermarking

• URL: http://arxiv.org/abs/2406.06979v2
• Date: Wed, 13 Nov 2024 08:41:50 GMT
• Title: AudioMarkBench: Benchmarking Robustness of Audio Watermarking
• Authors: Hongbin Liu, Moyang Guo, Zhengyuan Jiang, Lun Wang, Neil Zhenqiang Gong,
• Abstract summary: We present AudioMarkBench, the first systematic benchmark for evaluating the robustness of audio watermarking against watermark removal and watermark forgery. Our findings highlight the vulnerabilities of current watermarking techniques and emphasize the need for more robust and fair audio watermarking solutions.
• Score: 38.25450275151647
• License:
• Abstract: 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.

Related papers

• Improved Unbiased Watermark for Large Language Models [59.00698153097887]
  We introduce MCmark, a family of unbiased, Multi-Channel-based watermarks. MCmark preserves the original distribution of the language model. It offers significant improvements in detectability and robustness over existing unbiased watermarks.
  arXiv  Detail & Related papers  (2025-02-16T21:02:36Z)
• XAttnMark: Learning Robust Audio Watermarking with Cross-Attention [15.216472445154064]
  Cross-Attention Robust Audio Watermark (XAttnMark) This paper introduces Cross-Attention Robust Audio Watermark (XAttnMark), which bridges the gap by leveraging partial parameter sharing between the generator and the detector. We propose a psychoacoustic-aligned temporal-frequency masking loss that captures fine-grained auditory masking effects, enhancing watermark imperceptibility.
  arXiv  Detail & Related papers  (2025-02-06T17:15:08Z)
• Speech Watermarking with Discrete Intermediate Representations [45.892635912641836]
  We propose a novel speech watermarking framework that injects watermarks into the discrete intermediate representations of speech. DiscreteWM achieves state-of-the-art performance in robustness and imperceptibility, simultaneously. Our flexible frame-wise approach can serve as an efficient solution for both voice cloning detection and information hiding.
  arXiv  Detail & Related papers  (2024-12-18T14:57:06Z)
• Hidden in the Noise: Two-Stage Robust Watermarking for Images [25.731533630250798]
  We present a distortion-free watermarking method for images based on a diffusion model's initial noise. detecting the watermark requires comparing the initial noise reconstructed for an image to all previously used initial noises. We propose a two-stage watermarking framework for efficient detection.
  arXiv  Detail & Related papers  (2024-12-05T22:50:42Z)
• Certifiably Robust Image Watermark [57.546016845801134]
  Generative AI raises many societal concerns such as boosting disinformation and propaganda campaigns. Watermarking AI-generated content is a key technology to address these concerns. We propose the first image watermarks with certified robustness guarantees against removal and forgery attacks.
  arXiv  Detail & Related papers  (2024-07-04T17:56:04Z)
• WAVES: Benchmarking the Robustness of Image Watermarks [67.955140223443]
  WAVES (Watermark Analysis Via Enhanced Stress-testing) is a benchmark for assessing image watermark robustness. We integrate detection and identification tasks and establish a standardized evaluation protocol comprised of a diverse range of stress tests. We envision WAVES as a toolkit for the future development of robust watermarks.
  arXiv  Detail & Related papers  (2024-01-16T18:58:36Z)
• WavMark: Watermarking for Audio Generation [70.65175179548208]
  This paper introduces an innovative audio watermarking framework that encodes up to 32 bits of watermark within a mere 1-second audio snippet. The watermark is imperceptible to human senses and exhibits strong resilience against various attacks. It can serve as an effective identifier for synthesized voices and holds potential for broader applications in audio copyright protection.
  arXiv  Detail & Related papers  (2023-08-24T13:17:35Z)
• A Deep Learning-based Audio-in-Image Watermarking Scheme [1.1231577179316237]
  This paper presents a deep learning-based audio-in-image watermarking scheme. A neural network architecture is designed to automatically learn the watermarking process in an unsupervised manner. Experimental results have shown high fidelity and robustness of the proposed blind audio-in-image watermarking scheme.
  arXiv  Detail & Related papers  (2021-10-06T00:46:43Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.