Research
AUTEUR: Acoustic Plan Learning for Red-Teaming Text-to-Audio Models
AUTEUR introduces acoustic plan learning, a red-teaming framework that represents test prompts as structured acoustic plans covering foreground sounds, context, and vocal attributes. It trains a plan generator with supervised fine-tuning and reinforcement learning using waveform feedback while keeping the target text-to-audio model fixed. Experiments across four target systems report attack success rates of 79.4% on TangoFlux and 95.6% on Kling, with generated prompts transferring across open-source and closed-source models.
text-to-audio modelsAI red-teamingacoustic plan learning