SOURCE-LINKED INTELLIGENCE

InGuard: Towards Generalized Inner Guardrail for Safe Text-to-Image Generation

arXiv · AI, language, vision and robotics · article · Sep 23, 2026 · UTC

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 the generation pipeline and do not use the model's own representations. This separation can limit prompt-screening accuracy, while the image-side check runs only after the full generation cost has been

Read original source ↗ Open in workspace

recordType

paper

region

Global