T2SMark: Balancing Robustness and Diversity in Noise-as-Watermark for Diffusion Models

TL;DR

T2SMark introduces a novel two-stage watermarking method for diffusion models that balances robustness and diversity by embedding watermarks in reliable tail regions and using session keys for enhanced security.

Contribution

The paper proposes T2SMark, a two-stage Tail-Truncated Sampling scheme that improves robustness and diversity in Noise-as-Watermark methods for diffusion models.

Findings

Achieves optimal robustness-diversity balance in experiments

Effective on models with U-Net and DiT backbones

Code available for reproducibility

Abstract

Diffusion models have advanced rapidly in recent years, producing high-fidelity images while raising concerns about intellectual property protection and the misuse of generative AI. Image watermarking for diffusion models, particularly Noise-as-Watermark (NaW) methods, encode watermark as specific standard Gaussian noise vector for image generation, embedding the infomation seamlessly while maintaining image quality. For detection, the generation process is inverted to recover the initial noise vector containing the watermark before extraction. However, existing NaW methods struggle to balance watermark robustness with generation diversity. Some methods achieve strong robustness by heavily constraining initial noise sampling, which degrades user experience, while others preserve diversity but prove too fragile for real-world deployment. To address this issue, we propose T2SMark, a two-stage watermarking scheme based on Tail-Truncated Sampling (TTS). Unlike prior methods that simply map bits to positive or negative values, TTS enhances robustness by embedding bits exclusively in the reliable tail regions while randomly sampling the central zone to preserve the latent distribution. Our two-stage framework then ensures sampling diversity by integrating a randomly generated session key into both encryption pipelines. We evaluate T2SMark on diffusion models with both U-Net and DiT backbones. Extensive experiments show that it achieves an optimal balance between robustness and diversity. Our code is available at \href{https://github.com/0xD009/T2SMark}{https://github.com/0xD009/T2SMark}.