Phantom in the opera: adversarial music attack for robot dialogue system

Sheng Li, Jiyi Li, Yang Cao

Abstract

p>This study explores the vulnerability of robot dialogue systems' automatic speech recognition (ASR) module to adversarial music attacks. Specifically, we explore music as a natural camouflage for such attacks. We propose a novel method to hide ghost speech commands in a music clip by slightly perturbing its raw waveform. We apply our attack on an industry-popular ASR model, namely the time-delay neural network (TDNN), widely used for speech and speaker recognition. Our experiment demonstrates that adversarial music crafted by our attack can easily mislead industry-level TDNN models into picking up ghost commands with high success rates. However, it sounds no different from the original music to the human ear. This reveals a serious threat by adversarial music to robot dialogue systems, calling for effective defenses against such stealthy attacks.</p>
BibTeX
@article{li2024phantom,
  author = {Sheng Li and Jiyi Li and Yang Cao},
  title = {{Phantom in the opera: adversarial music attack for robot dialogue system}},
  journal = {Frontiers of Computer Science},
  year = {2024},
  doi = {10.3389/fcomp.2024.1355975},
}

Loading related content...

Figure