PLA trains adversarial prompts with a zero-order gradient method and multimodal CLIP losses to bypass safety filters and post-hoc checkers in black-box text-to-image models, outperforming earlier word-substitution attacks.
Available: https: //huggingface.co/stable- diffusion- v1- 5/ stable-diffusion-v1-5
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
PLA: Prompt Learning Attack against Text-to-Image Generative Models
PLA trains adversarial prompts with a zero-order gradient method and multimodal CLIP losses to bypass safety filters and post-hoc checkers in black-box text-to-image models, outperforming earlier word-substitution attacks.