paper-with-me

홈 › Papers

The Stable Signature: Rooting Watermarks in Latent Diffusion Models

2023-03-27 · ICCV 2023 1 · Pierre Fernandez, Guillaume Couairon, Hervé Jégou, Matthijs Douze, Teddy Furon

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$^{-6}$.

📄 PDF Abstract BibTeX arXiv:2303.15435

Code (3)

facebookresearch/stable_signature 공식 구현 pytorch
deepvk/metr pytorch
garvitbanga/robosignature pytorch

Tasks

Decoder

Methods 이 논문이 사용한 방법론

Test 설명 없음
Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Latent Watermark: Inject and Detect Watermarks in Latent Diffusion Space

2024-03-30 · Zheling Meng, Bo Peng, Jing Dong

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

2024-01-08 · Lijun Zhang, Xiao Liu, Antoni Viros Martin, Cindy Xiong Bearfield 외

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…

Denoising

WaterFlow: Learning Fast & Robust Watermarks using Stable Diffusion

2025-04-15 · Vinay Shukla, Prachee Sharma, Ryan Rossi, Sungchul Kim 외

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

2026-04-24 · Mathias Graf, Marco Willi, Melanie Mathys, Michael Aerni 외 arxiv

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

2025-03-14 · Jonas Thietke, Andreas Müller, Denis Lukovnikov, Asja Fischer 외

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