Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Back to Paper
cs.CVcs.CR

Local ID: 2603.26167v2

AI Summary: gemma4:e4b

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

By Yi Zhang, Hongbo Huang, Liang-Jie Zhang

Revision History Timeline

v13/27/2026
3/27/2026

“Accepted by CVPR 2026 Findings”

v24/8/2026
4/8/2026

“Accepted by CVPR 2026 Findings”

★ Version indexed in Explorer

Comparing v1 vs v2

Green = Added • Red = Removed

Title Comparison

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

Authors Comparison

No author changes.

v1 Comment

“Accepted by CVPR 2026 Findings”

v2 Comment

“Accepted by CVPR 2026 Findings”

Abstract Word Diff

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
View Full Version History on arXiv