SafeGen: Mitigating Unsafe Content Generation in Text-to-Image Models

arXiv:2404.06666v1 Announce Type: new
Abstract: Text-to-image (T2I) models, such as Stable Diffusion, have exhibited remarkable performance in generating high-quality images from text descriptions in recent years. However, text-to-image models may be tricked into generating not-safe-for-work (NSFW) content, particularly in sexual scenarios. Existing countermeasures mostly focus on filtering inappropriate inputs and outputs, or suppressing improper text embeddings, which can block explicit NSFW-related content (e.g., naked or sexy) but may still be vulnerable to adversarial prompts inputs that appear innocent but are …

abstract arxiv content generation cs.ai cs.cl cs.cr cs.cv diffusion filtering focus however image images inappropriate inputs nsfw performance quality safe stable diffusion text text-to-image type work