The Stable Signature: Rooting Watermarks in Latent Diffusion Models
- URL: http://arxiv.org/abs/2303.15435v2
- Date: Wed, 26 Jul 2023 07:19:58 GMT
- Title: The Stable Signature: Rooting Watermarks in Latent Diffusion Models
- Authors: Pierre Fernandez, Guillaume Couairon, Herv\'e J\'egou, Matthijs Douze
and Teddy Furon
- Abstract summary: 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.
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.
- Score: 29.209892051477194
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: 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$^{-6}$.
Related papers
- An undetectable watermark for generative image models [65.31658824274894]
We present the first undetectable watermarking scheme for generative image models.
In particular, an undetectable watermark does not degrade image quality under any efficiently computable metric.
Our scheme works by selecting the initial latents of a diffusion model using a pseudorandom error-correcting code.
arXiv Detail & Related papers (2024-10-09T18:33:06Z) - Trigger-Based Fragile Model Watermarking for Image Transformation Networks [2.38776871944507]
In fragile watermarking, a sensitive watermark is embedded in an object in a manner such that the watermark breaks upon tampering.
We introduce a novel, trigger-based fragile model watermarking system for image transformation/generation networks.
Our approach, distinct from robust watermarking, effectively verifies the model's source and integrity across various datasets and attacks.
arXiv Detail & Related papers (2024-09-28T19:34:55Z) - How to Trace Latent Generative Model Generated Images without Artificial Watermark? [88.04880564539836]
Concerns have arisen regarding potential misuse related to images generated by latent generative models.
We propose a latent inversion based method called LatentTracer to trace the generated images of the inspected model.
Our experiments show that our method can distinguish the images generated by the inspected model and other images with a high accuracy and efficiency.
arXiv Detail & Related papers (2024-05-22T05:33:47Z) - Stable Signature is Unstable: Removing Image Watermark from Diffusion Models [1.656188668325832]
We propose a new attack to remove the watermark from a diffusion model by fine-tuning it.
Our results show that our attack can effectively remove the watermark from a diffusion model such that its generated images are non-watermarked.
arXiv Detail & Related papers (2024-05-12T03:04:48Z) - RAW: A Robust and Agile Plug-and-Play Watermark Framework for AI-Generated Images with Provable Guarantees [33.61946642460661]
This paper introduces a robust and agile watermark detection framework, dubbed as RAW.
We employ a classifier that is jointly trained with the watermark to detect the presence of the watermark.
We show that the framework provides provable guarantees regarding the false positive rate for misclassifying a watermarked image.
arXiv Detail & Related papers (2024-01-23T22:00:49Z) - Towards Robust Model Watermark via Reducing Parametric Vulnerability [57.66709830576457]
backdoor-based ownership verification becomes popular recently, in which the model owner can watermark the model.
We propose a mini-max formulation to find these watermark-removed models and recover their watermark behavior.
Our method improves the robustness of the model watermarking against parametric changes and numerous watermark-removal attacks.
arXiv Detail & Related papers (2023-09-09T12:46:08Z) - T2IW: Joint Text to Image & Watermark Generation [74.20148555503127]
We introduce a novel task for the joint generation of text to image and watermark (T2IW)
This T2IW scheme ensures minimal damage to image quality when generating a compound image by forcing the semantic feature and the watermark signal to be compatible in pixels.
We demonstrate remarkable achievements in image quality, watermark invisibility, and watermark robustness, supported by our proposed set of evaluation metrics.
arXiv Detail & Related papers (2023-09-07T16:12:06Z) - Tree-Ring Watermarks: Fingerprints for Diffusion Images that are
Invisible and Robust [55.91987293510401]
Watermarking the outputs of generative models is a crucial technique for tracing copyright and preventing potential harm from AI-generated content.
We introduce a novel technique called Tree-Ring Watermarking that robustly fingerprints diffusion model outputs.
Our watermark is semantically hidden in the image space and is far more robust than watermarking alternatives that are currently deployed.
arXiv Detail & Related papers (2023-05-31T17:00:31Z) - PTW: Pivotal Tuning Watermarking for Pre-Trained Image Generators [42.0915430715226]
We propose Pivotal Tuning Watermarking (PTW), a method for watermarking pre-trained generators.
PTW can embed longer codes than existing methods while better preserving the generator's image quality.
We propose rigorous, game-based definitions for robustness and undetectability, and our study reveals that watermarking is not robust against an adaptive white-box attacker.
arXiv Detail & Related papers (2023-04-14T19:44:37Z) - Certified Neural Network Watermarks with Randomized Smoothing [64.86178395240469]
We propose a certifiable watermarking method for deep learning models.
We show that our watermark is guaranteed to be unremovable unless the model parameters are changed by more than a certain l2 threshold.
Our watermark is also empirically more robust compared to previous watermarking methods.
arXiv Detail & Related papers (2022-07-16T16:06:59Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.