SPOT projects prompts to a tau-safe set via total variation to cut inappropriate content 14-44% relative to baselines while preserving benign prompt behavior in frozen T2I models.
In parallel, guard-based models appear to effectively detect unsafe content; however, they suffer from a high rate of false positives
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
SPOT: Selective Prompt Projection via Total Variation for Inference-Only Safe Text-to-Image Generation
SPOT projects prompts to a tau-safe set via total variation to cut inappropriate content 14-44% relative to baselines while preserving benign prompt behavior in frozen T2I models.