SP-Guard: Selective Prompt-adaptive Guidance for Safe Text-to-Image Generation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915617912651776 |
|---|---|
| author | Yu, Sumin Moon, Taesup |
| author_facet | Yu, Sumin Moon, Taesup |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_11014 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SP-Guard: Selective Prompt-adaptive Guidance for Safe Text-to-Image Generation Yu, Sumin Moon, Taesup Computer Vision and Pattern Recognition Computers and Society I.2.8; I.2.10; K.4.2 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. |
| title | SP-Guard: Selective Prompt-adaptive Guidance for Safe Text-to-Image Generation |
| topic | Computer Vision and Pattern Recognition Computers and Society I.2.8; I.2.10; K.4.2 |
| url | https://arxiv.org/abs/2511.11014 |