Audio Pirates: Black-box Audio Watermark Removal via Diffusion Priors

• URL: http://arxiv.org/abs/2605.30614v1
• Date: Thu, 28 May 2026 22:07:32 GMT
• Title: Audio Pirates: Black-box Audio Watermark Removal via Diffusion Priors
• Abstract summary: We propose DiffErase, a black-box watermark removal attack that assumes no knowledge of the target watermarking scheme.<n>We show that DiffErase consistently removes watermarks while preserving perceptual quality across multiple audio domains.<n>These findings highlight the need for future audio watermarking designs to consider diffusion-based threats.
• Score: 44.562700127905295
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: With the rise of AI-generated audio, watermarking has become widely used for detecting misuse and protecting intellectual property. However, adversaries may try to remove these watermarks, making it critical to evaluate how well watermarking schemes withstand removal attacks. Existing attacks are often impractical: they either noticeably degrade perceptual quality or require access to the watermarking scheme. We propose DiffErase, a black-box watermark removal attack that assumes no knowledge of the target watermarking scheme while maintaining perceptual quality. DiffErase perturbs watermarked audio to an intermediate diffusion noise level and regenerates it using a pretrained denoising model, effectively suppressing watermark signals. Theoretical analysis and extensive experiments demonstrate that inaudible audio watermarks are highly vulnerable: across multiple audio domains, DiffErase consistently removes watermarks while preserving perceptual quality. These findings highlight the need for future audio watermarking designs to consider diffusion-based threats. Code and demos are available at https://differase.github.io/DiffErase/.

Related papers

• HarmonicAttack: An Adaptive Cross-Domain Audio Watermark Removal [12.931496380963802]
  A key defense against the misuse of AI-generated audio is by watermarking it, so that it can be easily distinguished from genuine audio.<n>Previous watermark removal schemes either assume impractical knowledge of the watermarks they are designed to remove or are computationally expensive.<n>We introduce HarmonicAttack, an efficient audio watermark removal method that only requires the basic ability to generate the watermarks.
  arXiv  Detail & Related papers  (2025-11-26T16:51:20Z)
• The Impact of Audio Watermarking on Audio Anti-Spoofing Countermeasures [5.250755043845844]
  This paper presents the first study on the impact of audio watermarking on spoofing countermeasures.<n>We construct watermark-augmented training and evaluation datasets, named the Watermark-Spoofing dataset.<n>Experiments show that watermarking consistently degrades anti-spoofing performance, with higher watermark density correlating with higher EERs.
  arXiv  Detail & Related papers  (2025-09-25T04:34:39Z)
• Yours or Mine? Overwriting Attacks against Neural Audio Watermarking [21.297468818273064]
  We develop a simple yet powerful attack that overwrites the legitimate audio watermark with a forged one.<n>Based on the audio watermarking information that the adversary has, we propose three categories of overwriting attacks.<n> Experimental results demonstrate that the proposed overwriting attacks can effectively compromise existing watermarking schemes.
  arXiv  Detail & Related papers  (2025-09-06T21:23:44Z)
• Forging and Removing Latent-Noise Diffusion Watermarks Using a Single Image [24.513881574366046]
  Previous watermarking schemes embed a secret key in the initial noise.<n>We propose a black-box adversarial attack without presuming access to the diffusion model weights.<n>We show that we can also apply a similar approach for watermark removal by learning perturbations to exit this region.
  arXiv  Detail & Related papers  (2025-04-27T18:29:26Z)
• Robust and Minimally Invasive Watermarking for EaaS [50.08021440235581]
  Embeds as a Service (Eding) is emerging as a crucial role in AI applications.<n>Eding is vulnerable to model extraction attacks, highlighting the need for copyright protection.<n>We propose a novel embedding-specific watermarking (ESpeW) mechanism to offer robust copyright protection for Eding.
  arXiv  Detail & Related papers  (2024-10-23T04:34:49Z)
• AudioMarkBench: Benchmarking Robustness of Audio Watermarking [38.25450275151647]
  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.
  arXiv  Detail & Related papers  (2024-06-11T06:18:29Z)
• Perceptive self-supervised learning network for noisy image watermark removal [59.440951785128995]
  We propose a perceptive self-supervised learning network for noisy image watermark removal (PSLNet) Our proposed method is very effective in comparison with popular convolutional neural networks (CNNs) for noisy image watermark removal.
  arXiv  Detail & Related papers  (2024-03-04T16:59:43Z)
• 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)
• Robustness of AI-Image Detectors: Fundamental Limits and Practical Attacks [47.04650443491879]
  We analyze the robustness of various AI-image detectors including watermarking and deepfake detectors. We show that watermarking methods are vulnerable to spoofing attacks where the attacker aims to have real images identified as watermarked ones.
  arXiv  Detail & Related papers  (2023-09-29T18:30:29Z)
• 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)
• Invisible Image Watermarks Are Provably Removable Using Generative AI [47.25747266531665]
  Invisible watermarks safeguard images' copyrights by embedding hidden messages only detectable by owners. We propose a family of regeneration attacks to remove these invisible watermarks. The proposed attack method first adds random noise to an image to destroy the watermark and then reconstructs the image.
  arXiv  Detail & Related papers  (2023-06-02T23:29:28Z)
• Certified Neural Network Watermarks with Randomized Smoothing [64.86178395240469]
  We propose a certifiable watermarking method for deep learning models. We show that our watermark is guaranteed to be unremovable unless the model parameters are changed by more than a certain l2 threshold. Our watermark is also empirically more robust compared to previous watermarking methods.
  arXiv  Detail & Related papers  (2022-07-16T16:06:59Z)

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.