PromptSafe uses LLM-rewritten safe prompts to train a gated soft prompt that suppresses NSFW content in text-to-image generation without image supervision or inference overhead.
Distorting embedding space for safety: A defense mechanism for adversarially robust dif- fusion models, 2025
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
PromptSafe: Gated Prompt Tuning for Safe Text-to-Image Generation
PromptSafe uses LLM-rewritten safe prompts to train a gated soft prompt that suppresses NSFW content in text-to-image generation without image supervision or inference overhead.