{"ID":2841544,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.11014","arxiv_id":"2511.11014","title":"SP-Guard: Selective Prompt-adaptive Guidance for Safe Text-to-Image Generation","abstract":"While diffusion-based T2I models have achieved remarkable image generation quality, they also enable easy creation of harmful content, raising social concerns and highlighting the need for safer generation. Existing inference-time guiding methods lack both adaptivity--adjusting guidance strength based on the prompt--and selectivity--targeting only unsafe regions of the image. Our method, SP-Guard, addresses these limitations by estimating prompt harmfulness and applying a selective guidance mask to guide only unsafe areas. Experiments show that SP-Guard generates safer images than existing methods while minimizing unintended content alteration. Beyond improving safety, our findings highlight the importance of transparency and controllability in image generation.","short_abstract":"While diffusion-based T2I models have achieved remarkable image generation quality, they also enable easy creation of harmful content, raising social concerns and highlighting the need for safer generation. Existing inference-time guiding methods lack both adaptivity--adjusting guidance strength based on the prompt--an...","url_abs":"https://arxiv.org/abs/2511.11014","url_pdf":"https://arxiv.org/pdf/2511.11014v1","authors":"[\"Sumin Yu\",\"Taesup Moon\"]","published":"2025-11-14T07:04:06Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.CY\"]","methods":"[\"Diffusion Model\"]","has_code":false}