The Stable Signature: Rooting Watermarks in Latent Diffusion Models
Generative image modeling enables a wide range of applications but raises ethical concerns about responsible deployment. This paper introduces an active strategy combining image watermarking and Latent Diffusion Models. The goal is for all generated images to conceal an invisible watermark allowing for future detection and/or identification. The method quickly fine-tunes the latent decoder of the image generator, conditioned on a binary signature. A pre-trained watermark extractor recovers the hidden signature from any generated image and a statistical test then determines whether it comes from the generative model. We evaluate the invisibility and robustness of the watermarks on a variety of generation tasks, showing that Stable Signature works even after the images are modified. For instance, it detects the origin of an image generated from a text prompt, then cropped to keep $10\%$ of the content, with $90$+$\%$ accuracy at a false positive rate below 10$^{-6}$.
Code (3)
Tasks
DecoderMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Latent Watermark: Inject and Detect Watermarks in Latent Diffusion Space
Watermarking is a tool for actively identifying and attributing the images generated by latent diffusion models. Existing methods face the dilemma of image quality and watermark robustness. Watermarks with superior image…
Attack-Resilient Image Watermarking Using Stable Diffusion
Watermarking images is critical for tracking image provenance and proving ownership. With the advent of generative models, such as stable diffusion, that can create fake but realistic images, watermarking has become part…
DenoisingWaterFlow: Learning Fast & Robust Watermarks using Stable Diffusion
The ability to embed watermarks in images is a fundamental problem of interest for computer vision, and is exacerbated by the rapid rise of generated imagery in recent times. Current state-of-the-art techniques suffer fr…
DeepSignature: Digitally Signed, Content-Encoding Watermarks for Robust and Transparent Image Authentication
AI-powered generative models have significantly expanded the possibilities for editing, manipulating, and creating high-quality images. Particularly, images that falsely appear to originate from trusted sources pose a se…
Towards A Correct Usage of Cryptography in Semantic Watermarks for Diffusion Models
Semantic watermarking methods enable the direct integration of watermarks into the generation process of latent diffusion models by only modifying the initial latent noise. One line of approaches building on Gaussian Sha…
Management