Red-Teaming Text-to-Image Models via In-Context Experience Replay and Semantic-Preserving Prompt Rewriting
ICER is a black-box framework that addresses the gap in text-to-image models in harmful content generation through two components: an LLM-based rewriter that produces fluent, natural-language adversarial prompts, and in-context experience replay that accumulates successful jailbreaking patterns into a reusable prior.
Zhi-Yi Chin, Pin-Yu Chen, Wei-Chen Chiu et al.
· 2 citations