all InfoSec news
GLAZE: Protecting Artists from Style Mimicry by Text-to-Image Models. (arXiv:2302.04222v1 [cs.CR])
cs.CR updates on arXiv.org arxiv.org
Recent text-to-image diffusion models such as MidJourney and Stable Diffusion
threaten to displace many in the professional artist community. In particular,
models can learn to mimic the artistic style of specific artists after
"fine-tuning" on samples of their art. In this paper, we describe the design,
implementation and evaluation of Glaze, a tool that enables artists to apply
"style cloaks" to their art before sharing online. These cloaks apply barely
perceptible perturbations to images, and when used as training data, …
art artist community design diffusion models evaluation learn midjourney mimicry protecting sharing stable diffusion text tool