Audio Adversarial Example Detection Using the Audio Style Transfer Learning Method
  • Kwon, Hyun
  • Lee, Kangjun
  • Ryu, Junyeol
  • Lee, Jun
Citations

WEB OF SCIENCE

7
Citations

SCOPUS

4

초록

In this paper, we propose a method for defending against audio adversarial examples that operates by applying audio style transfer learning. The proposed method has the effect of maintaining the classification result produced by the target model and removing the adversarial noise by changing only the style while maintaining the content of the input audio sample. In an experimental evaluation using the Mozilla Common Voice dataset as the test data source and TensorFlow as the machine learning library, the proposed method improved the target model's accuracy on the adversarial examples from 2.1% to 79.2% while maintaining its accuracy on the original samples at 81.4%.

키워드

Hidden Markov modelsFeature extractionDistortionSpeech recognitionMel frequency cepstral coefficientData modelsTransformersAcoustic systemsEvasion attackaudio domaindeep speechspeech recognitionsilent-hidden-voice attackDEEP NEURAL-NETWORKS
제목
Audio Adversarial Example Detection Using the Audio Style Transfer Learning Method
저자
Kwon, HyunLee, KangjunRyu, JunyeolLee, Jun
DOI
10.1109/ACCESS.2022.3216075
발행일
2025
유형
Article
저널명
IEEE Access
13
페이지
122464 ~ 122472