Learning to Evade: Adaptive Attacks on Audio Watermarking

• URL: http://arxiv.org/abs/2606.22310v1
• Date: Sun, 21 Jun 2026 02:35:22 GMT
• Title: Learning to Evade: Adaptive Attacks on Audio Watermarking
• Abstract summary: This paper introduces an adaptive audio watermark attack method (AWM) designed to bypass existing defense strategies.<n>AWM uses a two-stage optimization: the first stage ensures attack success, while the second improves audio quality.<n> evaluated on two watermarking methods across three voice datasets, AWM achieves high success while bypassing state-of-the-art detectors.
• Score: 28.60041167835628
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Advances in generative audio have intensified copyright concerns, making audio watermarking increasingly important for asserting ownership. However, existing audio watermarking methods are vulnerable to adversarial attacks. We find that watermark decoder message probabilities follow normal distributions, a property exploited by defenses to detect manipulations. This paper introduces an adaptive audio watermark attack method (AWM) designed to bypass existing defense strategies. AWM uses a two-stage optimization: the first stage ensures attack success, while the second improves audio quality. To evade detection, it estimates normal distribution parameters from limited samples of the target audio, and then adaptively steers decoded probabilities back into the estimated range. Evaluated on two watermarking methods across three voice datasets, AWM achieves high success while bypassing state-of-the-art detectors: detection rates are below 10% for replacement and creation, and 0% for removal.

Related papers

• Latent-Mark: An Audio Watermark Robust to Neural Resynthesis [62.09761127079914]
  Latent-Mark is the first zero-bit audio watermarking framework designed to survive semantic compression.<n>Our key insight is that robustness to the encode-decode process requires embedding the watermark within the invariant latent space.<n>Our work inspires future research into universal watermarking frameworks capable of maintaining integrity across increasingly complex and diverse generative distortions.
  arXiv  Detail & Related papers  (2026-03-05T15:51:09Z)
• T2SMark: Balancing Robustness and Diversity in Noise-as-Watermark for Diffusion Models [89.29541056113442]
  T2SMark is a two-stage watermarking scheme based on Tail-Truncated Sampling (TTS)<n>We evaluate T2SMark on diffusion models with both U-Net and DiT backbones.
  arXiv  Detail & Related papers  (2025-10-25T16:55:55Z)
• Character-Level Perturbations Disrupt LLM Watermarks [64.60090923837701]
  We formalize the system model for Large Language Model (LLM) watermarking.<n>We characterize two realistic threat models constrained on limited access to the watermark detector.<n>We demonstrate character-level perturbations are significantly more effective for watermark removal under the most restrictive threat model.<n> Experiments confirm the superiority of character-level perturbations and the effectiveness of the Genetic Algorithm (GA) in removing watermarks under realistic constraints.
  arXiv  Detail & Related papers  (2025-09-11T02:50:07Z)
• 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)
• SoK: How Robust is Audio Watermarking in Generative AI models? [6.241477455995664]
  To be effective, audio watermarks must resist removal attacks that distort signals to evade detection.<n>We investigate whether recent watermarking schemes that claim robustness can withstand a broad range of removal attacks.<n>We reproduce 9 watermarking schemes using open-source code, identify 8 new highly effective attacks, and highlight 11 key findings.
  arXiv  Detail & Related papers  (2025-03-24T21:57:59Z)
• XAttnMark: Learning Robust Audio Watermarking with Cross-Attention [15.216472445154064]
  Cross-Attention Robust Audio Watermark (XAttnMark)<n>This paper introduces Cross-Attention Robust Audio Watermark (XAttnMark), which bridges the gap by leveraging partial parameter sharing between the generator and the detector.<n>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)
• Optimizing Adaptive Attacks against Watermarks for Language Models [5.798432964668272]
  Large Language Models (LLMs) can be misused to spread unwanted content at scale.<n> watermarking deters misuse by hiding messages in content, enabling its detection using a secret watermarking key.<n>We formulate watermark robustness as an objective function and use preference-based optimization to tune adaptive attacks against the specific watermarking method.
  arXiv  Detail & Related papers  (2024-10-03T12:37:39Z)
• Proactive Detection of Voice Cloning with Localized Watermarking [50.13539630769929]
  We present AudioSeal, the first audio watermarking technique designed specifically for localized detection of AI-generated speech. AudioSeal employs a generator/detector architecture trained jointly with a localization loss to enable localized watermark detection up to the sample level. AudioSeal achieves state-of-the-art performance in terms of robustness to real life audio manipulations and imperceptibility based on automatic and human evaluation metrics.
  arXiv  Detail & Related papers  (2024-01-30T18:56:22Z)
• 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)
• An Unforgeable Publicly Verifiable Watermark for Large Language Models [84.2805275589553]
  Current watermark detection algorithms require the secret key used in the watermark generation process, making them susceptible to security breaches and counterfeiting during public detection. We propose an unforgeable publicly verifiable watermark algorithm named UPV that uses two different neural networks for watermark generation and detection, instead of using the same key at both stages.
  arXiv  Detail & Related papers  (2023-07-30T13:43:27Z)

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.