arXiv Open Access 2025

SP-Guard: Selective Prompt-adaptive Guidance for Safe Text-to-Image Generation

Sumin Yu Taesup Moon
Lihat Sumber

Abstrak

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.

Topik & Kata Kunci

Penulis (2)

S

Sumin Yu

T

Taesup Moon

Format Sitasi

Yu, S., Moon, T. (2025). SP-Guard: Selective Prompt-adaptive Guidance for Safe Text-to-Image Generation. https://arxiv.org/abs/2511.11014

Akses Cepat

Lihat di Sumber
Informasi Jurnal
Tahun Terbit
2025
Bahasa
en
Sumber Database
arXiv
Akses
Open Access ✓