RPG-RT iteratively fine-tunes an LLM with rule-based preferences from a decoupled CLIP scoring model, letting it rewrite prompts that bypass unknown safety defenses in black-box text-to-image systems.
Towards evaluating the robustness of neural networks
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.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling
RPG-RT iteratively fine-tunes an LLM with rule-based preferences from a decoupled CLIP scoring model, letting it rewrite prompts that bypass unknown safety defenses in black-box text-to-image systems.