Latent Watermark: Inject and Detect Watermarks in Latent Diffusion Space
Preprint
Abstract
Watermarking is a tool for actively identifying and attributing the images generated by latent diffusion models. Existing methods face the dilemma of watermark robustness and image quality. The reason for this dilemma is that watermark detection is performed in pixel space, implying an intrinsic link between image quality and watermark robustness. In this paper, we highlight that an effective solution to the problem is to both inject and detect watermarks in latent space, and propose Latent Watermark (LW) with a progressive training strategy. Experiments show that compared to the recently proposed methods such as StegaStamp, StableSignature, RoSteALS and TreeRing, LW not only surpasses them in terms of robustness but also offers superior image quality. When we inject 64-bit messages, LW can achieve an identification performance close to 100% and an attribution performance above 97% under 9 single-attack scenarios and one all-attack scenario. Our code will be available on GitHub.Keywords
All Related Versions
This publication has 5 references indexed in Scilit:
- Identifying and Mitigating the Security Risks of Generative AIFoundations and Trends® in Privacy and Security, 2023
- From image descriptions to visual denotations: New similarity metrics for semantic inference over event descriptionsTransactions of the Association for Computational Linguistics, 2014
- Making a “Completely Blind” Image Quality AnalyzerIEEE Signal Processing Letters, 2012
- Image Denoising by Sparse 3-D Transform-Domain Collaborative FilteringIEEE Transactions on Image Processing, 2007
- Image quality assessment: from error visibility to structural similarityIEEE Transactions on Image Processing, 2004