Gaussian Shannon: High-Precision Diffusion Model Watermarking Based on Communication

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Yi, Huang, Hongbo, Zhang, Liang-Jie
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914457281626112
author Zhang, Yi
Huang, Hongbo
Zhang, Liang-Jie
author_facet Zhang, Yi
Huang, Hongbo
Zhang, Liang-Jie
contents Diffusion models generate high-quality images but pose serious risks like copyright violation and disinformation. Watermarking is a key defense for tracing and authenticating AI-generated content. However, existing methods rely on threshold-based detection, which only supports fuzzy matching and cannot recover structured watermark data bit-exactly, making them unsuitable for offline verification or applications requiring lossless metadata (e.g., licensing instructions). To address this problem, in this paper, we propose Gaussian Shannon, a watermarking framework that treats the diffusion process as a noisy communication channel and enables both robust tracing and exact bit recovery. Our method embeds watermarks in the initial Gaussian noise without fine-tuning or quality loss. We identify two types of channel interference, namely local bit flips and global stochastic distortions, and design a cascaded defense combining error-correcting codes and majority voting. This ensures reliable end-to-end transmission of semantic payloads. Experiments across three Stable Diffusion variants and seven perturbation types show that Gaussian Shannon achieves state-of-the-art bit-level accuracy while maintaining a high true positive rate, enabling trustworthy rights attribution in real-world deployment. The source code have been made available at: https://github.com/Rambo-Yi/Gaussian-Shannon
format Preprint
id arxiv_https___arxiv_org_abs_2603_26167
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Gaussian Shannon: High-Precision Diffusion Model Watermarking Based on Communication
Zhang, Yi
Huang, Hongbo
Zhang, Liang-Jie
Computer Vision and Pattern Recognition
Cryptography and Security
Diffusion models generate high-quality images but pose serious risks like copyright violation and disinformation. Watermarking is a key defense for tracing and authenticating AI-generated content. However, existing methods rely on threshold-based detection, which only supports fuzzy matching and cannot recover structured watermark data bit-exactly, making them unsuitable for offline verification or applications requiring lossless metadata (e.g., licensing instructions). To address this problem, in this paper, we propose Gaussian Shannon, a watermarking framework that treats the diffusion process as a noisy communication channel and enables both robust tracing and exact bit recovery. Our method embeds watermarks in the initial Gaussian noise without fine-tuning or quality loss. We identify two types of channel interference, namely local bit flips and global stochastic distortions, and design a cascaded defense combining error-correcting codes and majority voting. This ensures reliable end-to-end transmission of semantic payloads. Experiments across three Stable Diffusion variants and seven perturbation types show that Gaussian Shannon achieves state-of-the-art bit-level accuracy while maintaining a high true positive rate, enabling trustworthy rights attribution in real-world deployment. The source code have been made available at: https://github.com/Rambo-Yi/Gaussian-Shannon
title Gaussian Shannon: High-Precision Diffusion Model Watermarking Based on Communication
topic Computer Vision and Pattern Recognition
Cryptography and Security
url https://arxiv.org/abs/2603.26167