Smark: A Watermark for Text-to-Speech Diffusion Models via Discrete Wavelet Transform

• URL: http://arxiv.org/abs/2512.18791v1
• Date: Sun, 21 Dec 2025 16:07:08 GMT
• Title: Smark: A Watermark for Text-to-Speech Diffusion Models via Discrete Wavelet Transform
• Abstract summary: This paper proposes a universal watermarking scheme for TTS diffusion models, termed Smark.<n>Smark operates in the common reverse diffusion paradigm shared by all TTS diffusion models.<n>Experiments are conducted to evaluate the audio quality and watermark performance in various simulated real-world attack scenarios.
• Score: 7.904062289123103
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Text-to-Speech (TTS) diffusion models generate high-quality speech, which raises challenges for the model intellectual property protection and speech tracing for legal use. Audio watermarking is a promising solution. However, due to the structural differences among various TTS diffusion models, existing watermarking methods are often designed for a specific model and degrade audio quality, which limits their practical applicability. To address this dilemma, this paper proposes a universal watermarking scheme for TTS diffusion models, termed Smark. This is achieved by designing a lightweight watermark embedding framework that operates in the common reverse diffusion paradigm shared by all TTS diffusion models. To mitigate the impact on audio quality, Smark utilizes the discrete wavelet transform (DWT) to embed watermarks into the relatively stable low-frequency regions of the audio, which ensures seamless watermark-audio integration and is resistant to removal during the reverse diffusion process. Extensive experiments are conducted to evaluate the audio quality and watermark performance in various simulated real-world attack scenarios. The experimental results show that Smark achieves superior performance in both audio quality and watermark extraction accuracy.

Related papers

• AudioNoisePrints: Model-free audio watermarking using spatial correlation in flow matching TTS [11.455535872504749]
  We present AudioNoisePrints, a training-free watermarking pipeline for flow matching and diffusion TTS models.<n>We exploited the fact that there are strong correlations between the initial Gaussian noises and the generated outputs in diffusion and flow matching models.<n>Our method outperforms AudioSeal, a strong baseline for audio watermarking under strong augmentations.
  arXiv  Detail & Related papers  (2026-08-23T02:52:37Z)
• Hidden in Plain Tokens: Simply Robust, Gradient-Free Watermark for Synthetic Audio [58.612001688217056]
  Inference-time watermarks for autoregressive models are unfit for continuous modalities due to discretization inconsistencies.<n>We propose an elegant solution for powerful and robust watermarking of synthetic audio.
  arXiv  Detail & Related papers  (2026-05-25T15:43:20Z)
• ShapeMark: Robust and Diversity-Preserving Watermarking for Diffusion Models [1.531886051127726]
  Noise-as-Watermark (NaW) approaches integrate watermarking directly into the diffusion process.<n>We introduce a dedicated randomization design that reshuffles the positions of noise elements without changing their values.<n>Our method achieves state-of-the-art robustness while maintaining high generation quality across a wide range of lossy scenarios.
  arXiv  Detail & Related papers  (2026-03-10T10:10:47Z)
• 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)
• OSI: One-step Inversion Excels in Extracting Diffusion Watermarks [56.210696479553945]
  We propose One-step Inversion (OSI), a significantly faster and more accurate method for extracting Gaussian Shading style watermarks.<n>OSI reformulates watermark extraction as a learnable sign classification problem, which eliminates the need for precise regression of the initial noise.<n>Our OSI substantially outperforms the multi-step diffusion inversion method: it is 20x faster, achieves higher extraction accuracy, and doubles the watermark payload capacity.
  arXiv  Detail & Related papers  (2026-02-10T07:43:16Z)
• WMVLM: Evaluating Diffusion Model Image Watermarking via Vision-Language Models [79.32764976020435]
  Digital watermarking is essential for securing generated images from diffusion models.<n>Previous watermark evaluation methods lack a unified framework for both residual and semantic watermarks.<n>We proposeLM, the first unified and interpretable evaluation framework for diffusion model image watermarking via vision-language models.
  arXiv  Detail & Related papers  (2026-01-29T12:14:32Z)
• 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)
• AWARE: Audio Watermarking with Adversarial Resistance to Edits [0.0]
  AWARE (Audio Watermarking with Adrial Resistance to Edits) is an approach that avoids reliance on attack-versa stacks and handcrafted differentiable distortions.<n> Embedding is obtained via adversarial optimization in the time-frequency domain under a level-proportional budget.<n>AWARE attains high audio quality and speech intelligibility (PESQ/STOI) and consistently low BER across various audio edits.
  arXiv  Detail & Related papers  (2025-10-20T13:10:52Z)
• StableGuard: Towards Unified Copyright Protection and Tamper Localization in Latent Diffusion Models [55.05404953041403]
  We propose a novel framework that seamlessly integrates a binary watermark into the diffusion generation process.<n>We show that StableGuard consistently outperforms state-of-the-art methods in image fidelity, watermark verification, and tampering localization.
  arXiv  Detail & Related papers  (2025-09-22T16:35:19Z)
• SOLIDO: A Robust Watermarking Method for Speech Synthesis via Low-Rank Adaptation [3.1682080884953736]
  We propose generative watermarking method that integrates parameter-efficient fine-tuning with speech watermarking.<n>The proposed method ensures high-fidelity watermarked speech even at a large capacity of 2000 bps.<n>It surpasses other state-of-the-art methods by nearly 23% in resisting time-stretching attacks.
  arXiv  Detail & Related papers  (2025-04-21T11:43:36Z)
• PT-Mark: Invisible Watermarking for Text-to-image Diffusion Models via Semantic-aware Pivotal Tuning [19.170393134039568]
  We present Semantic-aware Pivotal Tuning Watermarks (PT-Mark)<n>PT-Mark preserves both the semantics of diffusion images and the traceability of the watermark.<n>It achieves a 10% improvement in the performance of semantic preservation compared to state-of-the-art watermarking methods.
  arXiv  Detail & Related papers  (2025-04-15T04:25:57Z)
• SleeperMark: Towards Robust Watermark against Fine-Tuning Text-to-image Diffusion Models [77.80595722480074]
  SleeperMark is a framework designed to embed resilient watermarks into T2I diffusion models.<n>It guides the model to disentangle the watermark information from the semantic concepts it learns.<n>Our experiments demonstrate the effectiveness of SleeperMark across various types of diffusion models.
  arXiv  Detail & Related papers  (2024-12-06T08:44:18Z)
• GROOT: Generating Robust Watermark for Diffusion-Model-Based Audio Synthesis [37.065509936285466]
  This paper proposes the generative robust audio watermarking method (Groot) In this paradigm, the processes of watermark generation and audio synthesis occur simultaneously. Groot exhibits exceptional robustness when facing compound attacks, maintaining an average watermark extraction accuracy of around 95%.
  arXiv  Detail & Related papers  (2024-07-15T06:57:19Z)
• Invisible Watermarking for Audio Generation Diffusion Models [11.901028740065662]
  This paper presents the first watermarking technique applied to audio diffusion models trained on mel-spectrograms. Our model excels not only in benign audio generation, but also incorporates an invisible watermarking trigger mechanism for model verification.
  arXiv  Detail & Related papers  (2023-09-22T20:10:46Z)
• From Discrete Tokens to High-Fidelity Audio Using Multi-Band Diffusion [84.138804145918]
  Deep generative models can generate high-fidelity audio conditioned on various types of representations. These models are prone to generate audible artifacts when the conditioning is flawed or imperfect. We propose a high-fidelity multi-band diffusion-based framework that generates any type of audio modality from low-bitrate discrete representations.
  arXiv  Detail & Related papers  (2023-08-02T22:14:29Z)
• Intellectual Property Protection of Diffusion Models via the Watermark Diffusion Process [22.38407658885059]
  This paper introduces WDM, a novel watermarking solution for diffusion models without imprinting the watermark during task generation. It involves training a model to concurrently learn a Watermark Diffusion Process (WDP) for embedding watermarks alongside the standard diffusion process for task generation.
  arXiv  Detail & Related papers  (2023-06-06T06:31:07Z)

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.