A reinforcement-learning red-team LLM generates stealthy prompts that bypass text-to-image safety filters and produce toxic images, with reported transfer success against commercial APIs.
Title resolution pending
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.CR 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
GenBreak: Red Teaming Text-to-Image Generators Using Large Language Models
A reinforcement-learning red-team LLM generates stealthy prompts that bypass text-to-image safety filters and produce toxic images, with reported transfer success against commercial APIs.