cs.AINov 6, 2026

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

Authors: Jiashu Zhang, Jiaming He, Zheming Zhang, Kaizheng Wang, Bing Li, Zhiyuan Zha, Yi Yu

Organizations: Jilin University · Nanyang Technological University

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 key idea is to represent test descriptions as structured acoustic plans that organize foreground sounds, context, and vocal attributes. To this end, we propose acoustic plan learning, a framework that learns and refines these plans using waveform feedback. We train the plan generator through supervised fine-tuning followed by reinforcement learning with audio feedback while keeping the target audio model fixed. At inference time, the same trained model generates initial plans and uses feedback to revise their context and vocal attributes while preserving the foreground. Experiments across four target systems show attack success rates of 79.4% on TangoFlux and 95.6% on Kling. The resulting test prompts also transfer across open-source and closed-source models, indicating shared acoustic vulnerabilities.

Figures & tables

Explore similar work

CardsList
  1. ARENA: Automated Red-Teaming for Large Audio Language Models

    Aug 16, 2026Jiaming He, Zhicong Huang, Tian Jin +5Audio-Language Model Evaluation

  2. FoeGlass: Simple In-Context Learning Is Enough for Red Teaming Audio Deepfake Detectors

    Jun 3, 2026Sepehr Dehdashtian, Jacob H Seidman, Vishnu N Boddeti +1Audio Deepfake DetectionAdversarial Robustness