Latent Guard: a Safety Framework for Text-to-image Generation

arXiv:2404.08031v1 Announce Type: cross
Abstract: With the ability to generate high-quality images, text-to-image (T2I) models can be exploited for creating inappropriate content. To prevent misuse, existing safety measures are either based on text blacklists, which can be easily circumvented, or harmful content classification, requiring large datasets for training and offering low flexibility. Hence, we propose Latent Guard, a framework designed to improve safety measures in text-to-image generation. Inspired by blacklist-based approaches, Latent Guard learns a latent space on top of …

arxiv cs.ai cs.cv cs.lg framework image image generation safety text text-to-image type