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

arXiv:2306.04744v3 Announce Type: replace
Abstract: The rapid advancement of generative models, facilitating the creation of hyper-realistic images from textual descriptions, has concurrently escalated critical societal concerns such as misinformation. Although providing some mitigation, traditional fingerprinting mechanisms fall short in attributing responsibility for the malicious use of synthetic images. This paper introduces a novel approach to model fingerprinting that assigns responsibility for the generated images, thereby serving as a potential countermeasure to model misuse. Our method modifies generative models based on …

arxiv attribution cs.cv diffusion diffusion models image image diffusion text text-to-image type