AUTEUR: Acoustic Plan Learning for Red-Teaming Text-to-Audio Models

arXiv:2611.09351v1 Announce Type: new Abstract: Automated red-teaming of text-to-audio models requires test prompts that pass textual screening and expose harmful acoustic content. The central challenge is to connect the sounds produced by the target model to both reusable test generation and prompt revision. Our…

Excerpt provided by arXiv cs.AI via its public feed. Full reporting belongs to the original publisher.