Could It Be Generated? Towards Practical Analysis of Memorization in Text-To-Image Diffusion Models

arXiv:2405.05846v1 Announce Type: cross
Abstract: The past few years have witnessed substantial advancement in text-guided image generation powered by diffusion models. However, it was shown that text-to-image diffusion models are vulnerable to training image memorization, raising concerns on copyright infringement and privacy invasion. In this work, we perform practical analysis of memorization in text-to-image diffusion models. Targeting a set of images to protect, we conduct quantitive analysis on them without need to collect any prompts. Specifically, we first formally define …

abstract advancement analysis arxiv concerns copyright copyright infringement cs.cr cs.cv diffusion diffusion models generated however image image diffusion image generation infringement practical privacy text text-to-image training type vulnerable work