ShapeMark: Robust and Diversity-Preserving Watermarking for Diffusion Models

2026-03-10

AI Summary

Existing watermarking methods for diffusion models struggle to simultaneously preserve generation diversity and ensure robust copyright protection. This work proposes a structured noise pattern–based watermarking mechanism that embeds identifiable noise structures during the diffusion process, coupled with a position-randomization strategy. This approach significantly enhances watermark robustness against various lossy operations—such as compression, cropping, and filtering—without compromising image fidelity or generation diversity. Experimental results demonstrate that the proposed method achieves state-of-the-art watermark robustness while maintaining high-quality and diverse image synthesis.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Adversarial Learning & Robustness
• Natural Language Processing: Generation

Application Category

• Web Mining and Content Analysis: Content-based information diffusion
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Responsible Web: Data and user privacy-enhancing technologies for the Web

Abstract

Diffusion models have made substantial advances in recent years, enabling high-quality image synthesis; however, the widespread dissemination and reuse of their outputs have introduced new challenges in intellectual property protection and content provenance. Image watermarking offers a solution to these challenges, and recent work has increasingly explored Noise-as-Watermark (NaW) approaches that integrate watermarking directly into the diffusion process. However, existing NaW methods fail to balance robustness and diversity. We attribute this weakness to value encoding, which encodes watermark bits into individual sampled values. It is extremely fragile in practical application scenarios. To address this, we encode watermark bits into the structured noise pattern, so that the watermark is preserved even when individual values are perturbed. To further ensure generation diversity, we introduce a dedicated randomization design that reshuffles the positions of noise elements without changing their values, preventing the watermark from inducing fixed noise patterns or spatial locations. Extensive experiments demonstrate that our method achieves state-of-the-art robustness while maintaining high generation quality across a wide range of lossy scenarios.

Problem

• watermarking
• diffusion models
• robustness
• diversity
• Noise-as-Watermark

Innovation

• structured noise pattern
• Noise-as-Watermark
• diversity preservation
• robust watermarking
• diffusion models