Skip to content
Preprint

CLaW: Codec-Guided Adaptive Latent Watermarking for Traceable Diffusion Image Generation

Oct 2026 · 0 citations · 57 references
Computer Science

TL;DR

ClaW (Codec-guided Latent Watermarking) is proposed, a robust and efficient watermarking framework for traceable diffusion image generation with frozen diffusion backbones and inversion-free detection and achieves state-of-the-art robustness under image transformations, enabling reliable user-level traceability.

Abstract

With the rapid advancement of text-to-image diffusion models, increasingly realistic AI-generated content has raised serious concerns about misuse and copyright infringement. Digital watermarking offers a promising solution by enabling user-level traceability, yet existing methods remain difficult to deploy at scale, hindered by costly model retraining or detection, poor effectiveness-fidelity trade-offs, and limited robustness to image transformations. To address these challenges, we propose CLaW (Codec-guided Latent Watermarking), a robust and efficient watermarking framework for traceable diffusion image generation with frozen diffusion backbones and inversion-free detection. Specifically, CLaW first uses a pretrained watermark codec to map each watermark message to a latent residual, enabling low-cost sampling-time injection. Then, the residual is injected within a late denoising window, where image semantics are better preserved and the watermark signal is less perturbed by subsequent denoising updates, yielding a better balance between watermark effectiveness and image fidelity. Furthermore, we introduce a decoder-guided adaptive injection mechanism that uses decoding confidence as feedback to dynamically calibrate watermark strength, reinforcing weak watermark signals and improving robustness under image transformations. Extensive experiments show that CLaW preserves high visual fidelity and achieves state-of-the-art robustness under image transformations, enabling reliable user-level traceability.

View source

Similar papers

Preprint Oct 2026

SAMP: Self-Adaptive Margin Prioritization For Robust Diffusion Watermarking

Diffusion models have made high-fidelity visual generation widely accessible, while also lowering the barrier to producing convincing visual forgeries and complicating content provenance. Existing watermarking methods typically use a fixed embedding strength throughout denoising or treat all watermark dimensions equall...

Yu-Hao Xue, Jiu-An Zhou, Yu Cheng et al. · 0 citations
Preprint Oct 2026

Attack-Resilient Multi-Bit Image Watermarking Framework via Latent Coordinate Sign Clamping

Watermarking is essential for image copyright protection and attribution, yet existing methods suffer from fundamental trade-offs among post-hoc applicability to pre-existing images, multi-bit capacity, training-free deployment, and adversarial resilience. To address these limitations, we propose a training-free waterm...

Marjan Beheshti, Rong-Hua Xu · 0 citations
Preprint Oct 2026

WaveMark: Robust Wavelet-Domain Image Watermarking for Diffusion Models

WaveMark is a novel wavelet-domain watermarking method that embeds messages in a diffusion model's initial noise to support robust recovery from perturbed carriers, and distributes keyed replicas of message bits across spatial positions, wavelet orientations, and scales.

Jie Cao, Qi Li, Chaklam Cheong et al. · 0 citations
Sep 2026

Persistent Watermarking of Text-to-Image Models

This work proposes a contrastive-style watermarking objective with a term that explicitly encourages the watermarked model to behave differently from the original model on trigger inputs, resulting in substantially stronger trigger-data persistence than prior methods.

Di-Xi Yao, Kai-Wen Chen, Tahseen Rabbani et al. · 0 citations
Sep 2026

FeatMark: Feature-level Watermark Protection against Mimicry Attacks with Diffusion Models

FeatMark is introduced, a watermarking framework that shifts from pixel-level, energy-starved perturbations to inconspicuous semantic features: small, scene-consistent micro- features that remain natural to humans while providing a stronger, machine-verifiable provenance signal.

Hao-Yang Li, Ruo-Xi Sun, Qing-Qing Ye et al. · 0 citations
Sep 2026

COVER: Codec-Robust Video Watermarking with Generative Video Priors

COLD is presented, the first learned video watermark built around codec compression as its design target, which survives that compression by embedding the payload in the latent space of a frozen generative video autoencoder and recovering it by re-encoding the received video into that same latent space.

Yu-Xin Cao, Hao Yang, Zi-Qi Ding et al. · 1 citation

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.