BiSLW: Bi-Spectral Latent Watermarking for Generative Diffusion Models

• URL: http://arxiv.org/abs/2607.02643v1
• Date: Thu, 02 Jul 2026 17:48:54 GMT
• Title: BiSLW: Bi-Spectral Latent Watermarking for Generative Diffusion Models
• Abstract summary: BiSLW is a trainable bi-spectral latent watermarking framework that embeds aligned identity signals across complementary spectral bands.<n>Low-frequency components encode global semantics, while high-frequency components capture fine texture.<n>BiSLW achieves a strong balance between fidelity and robustness, improving PSNR by over 3 dB compared to prior latent diffusion watermarking methods.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Diffusion-based generative models have transformed visual content synthesis, yet they remain vulnerable to unauthorized usage and lack reliable attribution methods. Existing watermarking techniques often treat latent tensors as static spatial feature maps or depend on pixel-domain modification, and most do not explicitly leverage the internal frequency structure of the latent space for dual-band redundant embedding, leaving them susceptible to the stochastic nature of diffusion and regeneration attacks. We introduce BiSLW, a trainable bi-spectral latent watermarking framework that jointly embeds aligned identity signals across complementary spectral bands of the decoded diffusion latent using learned encoders and decoders, going beyond fixed-pattern frequency approaches. We leverage the inherent frequency structure of diffusion latents to design a dual-band watermarking framework. Low-frequency components encode global semantics, while high-frequency components capture fine texture. We exploit this structure to embed watermarks across complementary spectral bands. The watermark is independently injected into both bands via learned encoders and recombined before decoding, ensuring it becomes intrinsic to the generative trajectory. Dual spectral decoders recover the watermark from each band, while a cross-band consistency constraint enforces alignment between semantic and textural embeddings. Experiments show that BiSLW achieves a strong balance between perceptual fidelity and robustness, improving PSNR by over 3 dB compared to prior latent diffusion watermarking methods while preserving near-perfect bit accuracy under aggressive regeneration and common distortions, all with negligible computational overhead.

Related papers

• WAVE: Reversing the Guidance Hierarchy for Coarse-to-Fine Guided Depth Super-Resolution [50.15623093332659]
  Guided depth super-resolution (GDSR) typically extracts RGB guidance features through convolutional hierarchies, inheriting their fine-to-coarse bias.<n>We present WAVE, which introduces a multi-level discrete wavelet transform (ML-DWT) as an explicit and interpretable feature-control mechanism.<n>WAVE exploits sub-bands to treat high- and low-frequency content separately, filtering at its source the misleading RGB color and texture cues.
  arXiv  Detail & Related papers  (2026-08-26T02:16:41Z)
• SpreadMark: Robust Image Watermarking via Spread-Spectrum Embedding [35.24760637584417]
  We revisit spread-spectrum embedding, a classical watermarking principle, inside a modern neural post-hoc watermarking architecture.<n>Our starting point is a measurement: in existing encoder-decoder schemes each message bit occupies only a small fraction of the image.<n> SpreadMark spreads each bit as a dense pseudo-random codeword over the whole image and recovers it by matched-filtering a learned cover-suppressed chip representation.
  arXiv  Detail & Related papers  (2026-08-04T05:52:17Z)
• Dual-Guard: Dual-Channel Latent Watermarking for Provenance and Tamper Localization in Diffusion Images [19.688873186557483]
  We propose Dual-Guard, a dual-channel latent watermarking framework for provenance verification, framing resistance, and region-level tamper localization.<n>In Full mode, Dual-Guard keeps clean-image authentication false rejection and tamper false alarm below one half of one percent, while maintaining near-complete detection under reprompting, diffusion editing, and eight local tampering attacks.
  arXiv  Detail & Related papers  (2026-04-21T05:03:42Z)
• BiGain: Unified Token Compression for Joint Generation and Classification [47.040577759493004]
  BiGain is a training-free, plug-and-play framework that preserves generation quality while improving classification in accelerated diffusion models.<n>Our key insight is frequency separation, which disentangles fine detail from global semantics, enabling compression that respects both generative fidelity and discriminative utility.<n>Our analyses indicate that balanced spectral retention, preserving high-frequency detail and low/mid-frequency semantics, is a reliable design rule for token compression in diffusion models.
  arXiv  Detail & Related papers  (2026-03-12T17:55:53Z)
• 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)
• SKeDA: A Generative Watermarking Framework for Text-to-video Diffusion Models [40.540302276054376]
  We propose a generative watermarking framework tailored for text-to-video diffusion models.<n> SKeDA consists of two components: (1) Shuffle-Key-based Distribution-preserving Sampling (SKe) employs a single base pseudo-random binary sequence for watermark encryption and derives frame-level encryption sequences through permutation.<n>Extensive experiments demonstrate that SKeDA preserves high video generation quality and watermark robustness.
  arXiv  Detail & Related papers  (2026-02-27T06:18:03Z)
• 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)
• An Ensemble Framework for Unbiased Language Model Watermarking [60.99969104552168]
  We propose ENS, a novel ensemble framework that enhances the detectability and robustness of unbiased watermarks.<n>ENS sequentially composes multiple independent watermark instances, each governed by a distinct key, to amplify the watermark signal.<n> Empirical evaluations show that ENS substantially reduces the number of tokens needed for reliable detection and increases resistance to smoothing and paraphrasing attacks.
  arXiv  Detail & Related papers  (2025-09-28T19:37:44Z)
• 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)

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.