SLIM: Stable Latent Integration for Robust Watermark in Diffusion Model

View at publisher Summarise with VIRAT
Authors: Xiaoxi Kong, Pengdi Chen, Bin Li, Jieyu Yuan, Zhanchuan Cai, Hao Wu, Lifeng Liang
Cited by: 0
References: 53

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Embedding watermarks in the diffusion latent space improves robustness but often alters visual content due to the distribution shift between watermarked and clean latent variables. To address this issue, stable latent integration watermark (SLIM) is proposed in this paper, in which watermarks are integrated into the features output by the noise prediction network of a diffusion model, while ensuring that the perturbation introduced in the diffusion latent space remains negligible. Specifically, a watermark encoder–decoder is first trained to convert binary watermark sequences into watermark latent variables that are dimensionally compatible with the diffusion latent variables, enabling flexible and reliable embedding and extraction. The watermark latent variables are processed through the first down-sampling block of the denoising U-Net, and the resulting watermark features are fused with the block output to minimize interference with image semantics. To counteract the perturbations in diffusion features induced by watermark embedding and to ensure accurate watermark extraction, the denoising U-Net is efficiently fine-tuned using a low-rank adaptation module. Experimental results demonstrate that SLIM achieves superior generation quality while exhibiting exceptional robustness against diverse attacks compared with baseline methods. Code will be available at https://github.com/XiaoxiKong/SLIM.

Fields of Study & Subjects

Advanced Steganography and Watermarking Techniques Digital Media Forensic Detection Adversarial Robustness in Machine Learning

Publication details

Journal / source
IEEE Transactions on Circuits and Systems for Video Technology
Volume
36
Issue
7
Pages
10036–10049
Publication date
20 March 2026
Language
EN