The Stable Signature: Rooting Watermarks in Latent Diffusion Models

by   Pierre Fernandez, et al.

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.


page 5

page 15

page 16

page 17

page 19

page 20

page 21

page 22


Securing Deep Generative Models with Universal Adversarial Signature

Recent advances in deep generative models have led to the development of...

WOUAF: Weight Modulation for User Attribution and Fingerprinting in Text-to-Image Diffusion Models

The rapid advancement of generative models, facilitating the creation of...

Latent Diffusion for Language Generation

Diffusion models have achieved great success in modeling continuous data...

Training on Thin Air: Improve Image Classification with Generated Data

Acquiring high-quality data for training discriminative models is a cruc...

LDM3D: Latent Diffusion Model for 3D

This research paper proposes a Latent Diffusion Model for 3D (LDM3D) tha...

Detecting Images Generated by Diffusers

This paper explores the task of detecting images generated by text-to-im...

Can AI Put Gamma-Ray Astrophysicists Out of a Job?

In what will likely be a litany of generative-model-themed arXiv submiss...

Please sign up or login with your details

Forgot password? Click here to reset