TIIS (한국인터넷정보학회)
Current Result Document :
| 한글제목(Korean Title) |
Defending and Detecting Audio Adversarial Example using Frame Offsets |
| 영문제목(English Title) |
Defending and Detecting Audio Adversarial Example using Frame Offsets |
| 저자(Author) |
Yongkang Gong
Diqun Yan
Terui Mao
Donghua Wang
Rangding Wang
|
| 원문수록처(Citation) |
VOL 15 NO. 4 PP. 1538 ~ 1552 (2021. 04) |
한글내용
(Korean Abstract) |
|
영문내용
(English Abstract) |
Machine learning models are vulnerable to adversarial examples generated by adding a deliberately designed perturbation to a benign sample. Particularly, for automatic speech recognition (ASR) system, a benign audio which sounds normal could be decoded as a harmful command due to potential adversarial attacks. In this paper, we focus on the countermeasures against audio adversarial examples. By analyzing the characteristics of ASR systems, we find that frame offsets with silence clip appended at the beginning of an audio can degenerate adversarial perturbations to normal noise. For various scenarios, we exploit frame offsets by different strategies such as defending, detecting and hybrid strategy. Compared with the previous methods, our proposed method can defense audio adversarial example in a simpler, more generic and efficient way. Evaluated on three state-of-the-arts adversarial attacks against different ASR systems respectively, the experimental results demonstrate that the proposed method can effectively improve the robustness of ASR systems.
|
| 키워드(Keyword) |
Speech Recognition Safety
Adversarial Defense
Adversarial Detection
Audio Adversarial Example
ASR
|
| 파일첨부 |
PDF 다운로드
|
