| Autor: |
Sheng Li, Jiyi Li, Yang Cao |
| Jazyk: |
angličtina |
| Rok vydání: |
2024 |
| Předmět: |
|
| Zdroj: |
Frontiers in Computer Science, Vol 6 (2024) |
| Druh dokumentu: |
article |
| ISSN: |
2624-9898 |
| DOI: |
10.3389/fcomp.2024.1355975 |
| Popis: |
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. |
| Databáze: |
Directory of Open Access Journals |
| Externí odkaz: |
|
