DiffuseTrace: A Transparent and Flexible Watermarking Scheme for Latent Diffusion Model
This addresses copyright tracking and risk mitigation for AI-generated content, offering a flexible plug-in solution for diffusion models.
The paper tackles the problem of illegal use of Latent Diffusion Models by proposing DiffuseTrace, a watermarking scheme that embeds multi-bit watermarks without compromising image quality, achieving a 99% detection rate and over 94% attribution accuracy under various attacks.
Latent Diffusion Models (LDMs) enable a wide range of applications but raise ethical concerns regarding illegal utilization. Adding watermarks to generative model outputs is a vital technique employed for copyright tracking and mitigating potential risks associated with Artificial Intelligence (AI)-generated contents. However, post-processed watermarking methods are unable to withstand generative watermark attacks and there exists a trade-off between image fidelity and watermark strength. Therefore, we propose a novel technique called DiffuseTrace. DiffuseTrace does not rely on fine-tuning of the diffusion model components. The multi-bit watermark is a embedded into the image space semantically without compromising image quality. The watermark component can be utilized as a plug-in in arbitrary diffusion models. We validate through experiments the effectiveness and flexibility of DiffuseTrace. Under 8 types of image processing watermark attacks and 3 types of generative watermark attacks, DiffuseTrace maintains watermark detection rate of 99% and attribution accuracy of over 94%.