InGuard: Towards Generalized Inner Guardrail for Safe Text-to-Image Generation
Modern text-to-image (T2I) models generate high-quality images from arbitrary user prompts, yet they can just as easily produce not-safe-for-work (NSFW) content. Conventional outer guardrails consist of two components: a prompt classifier that checks for risk before generation, and a post-hoc image classifier that checks the fully generated image. In this design, both classifiers operate outside…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.
