Ghost in the Radio: An Audio Adversarial Attack Using Environmental Noise Through Radio

Many automatic speech recognition (ASR) systems provide functions such as sending messages or opening garage doors. If such a system malfunctions, it could pose a significant threat. In this paper, we propose the attack scenario in which we transfer audio adversarial examples to radio system through...

Full description

Saved in:
Bibliographic Details
Published in:IEEE access 2024, Vol.12, p.171718-171727
Main Authors: Choi, Hyeongjun, Jung, Ji Hyuk, Yoon, Ji Won
Format: Article
Language:English
Subjects:
Accuracy
Adversarial attack
Adversarial machine learning
artificial intelligence
Automatic speech recognition
Automobiles
environmental noise
Frequency modulation
Mathematical models
Microphones
Music
Noise measurement
over-the-air
Video on demand
Wireless networks
Working environment noise
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Many automatic speech recognition (ASR) systems provide functions such as sending messages or opening garage doors. If such a system malfunctions, it could pose a significant threat. In this paper, we propose the attack scenario in which we transfer audio adversarial examples to radio system through the radio signal and the sound received through radio deceives the ASR system. In addition, we propose over-the-air technology using environmental noise so that we can attack easily and effectively. Using this method, we observed that the combined sound was much more robust to environmental noise than the non-combined sound. Finally, we experiment as our scenario on a real environment with adversarial examples created using environmental noise and show the results. Our attack succeeded against commercial ASR systems with a success rate of over 50%.
ISSN:2169-3536
2169-3536
DOI:10.1109/ACCESS.2024.3492273