收藏切换
Perturbation Analysis of the Vital Region in Speech Adversarial Example Based on Frame Structure
收藏切换
Songshen Han1, 2, Songhui Guo1, 2, *, Kaiyong Xu1, 2, Bo Yang1, Miao Yu1
Journal of Computer Research and Development | 2024, 61(3) : 685 - 700
Less
收藏切换
Journal of Computer Research and Development | 2024, 61(3): 685-700
• Artificial Intelligence •
Perturbation Analysis of the Vital Region in Speech Adversarial Example Based on Frame Structure
Full
Songshen Han1, 2, Songhui Guo1, 2, *, Kaiyong Xu1, 2, Bo Yang1, Miao Yu1
Affiliations
  • 1Strategic Support Force Information Engineering University, Zhengzhou 450001
  • 2Henan Key Laboratory of Information Security (Strategic Support Force Information Engineering University), Zhengzhou 450001
  • born in 1999. Master. His main research interests include artificial intelligence security and cloud computing security

    born in 1979. PhD, professor. His main research interests include 5G security and cloud computing security

    born in 1963. PhD, professor. His main research interests include information security and trusted computing

    born in 1993. PhD candidate. His main research interests include deep learning, and intelligent system security testing and evaluation

    born in 1987. Master candidate. His main research interests include artificial intelligence security and natural language processing

About Author:

born in 1999. Master. His main research interests include artificial intelligence security and cloud computing security

born in 1979. PhD, professor. His main research interests include 5G security and cloud computing security

born in 1963. PhD, professor. His main research interests include information security and trusted computing

born in 1993. PhD candidate. His main research interests include deep learning, and intelligent system security testing and evaluation

born in 1987. Master candidate. His main research interests include artificial intelligence security and natural language processing

Published: 2024-03-02 doi: 10.7544/issn1000-1239.202221034
Outline
收藏切换

At present, adversarial attacks on speech recognition models have typically involved adding noise to the entire speech signal, resulting in a wide perturbation range and introducing high-frequency noise. Existing research has attempted to reduce the perturbation range by designing optimization targets. However, controlling the transcription result requires adding perturbations to each frame, thus limiting further reduction in perturbation range. To address this issue, we propose a novel approach that examines the feature extraction process of speech recognition systems from a frame structure perspective. The study finds that framing and windowing determine the distribution of critical regions within the frame structure. Specifically, the weight of adding perturbation to each sampling point within the frame is influenced by its location. Based on the results of perturbation analysis on input features, we partition regions with shared attributes. Then we propose the adversarial example space measurement method and evaluation index to quantify the weight of sampling points for adversarial examples generation. We conduct cross-experiments by adding perturbations at different intervals within the frame, which enables us to identify key regions for perturbation addition. Our experiments on multiple models demonstrate that adding adversarial perturbation to vital regions can narrow the perturbation range, and provide a new perspective for generating high-quality audio adversarial examples.

speech recognition  /  adversarial attack  /  input feature  /  perturbation analysis  /  adversarial example space metric
韩松莘, 郭松辉, 徐开勇, 杨博, 于淼. 基于帧结构的语音对抗样本重点区域扰动分析. 计算机研究与发展, 2024 , 61 (3) : 685 -700 . DOI: 10.7544/issn1000-1239.202221034
Songshen Han, Songhui Guo, Kaiyong Xu, Bo Yang, Miao Yu. Perturbation Analysis of the Vital Region in Speech Adversarial Example Based on Frame Structure[J]. Journal of Computer Research and Development, 2024 , 61 (3) : 685 -700 . DOI: 10.7544/issn1000-1239.202221034
Year 2024 volume 61 Issue 3
74
35
Cite this Article
BibTeX
Article Info
doi: 10.7544/issn1000-1239.202221034
  • Receive Date:2022-12-20
  • Online Date:2026-11-17
  • Published:2024-03-02
Article Data
Affiliations
History
  • Received:2022-12-20
  • Revised:2023-05-04
Affiliations
    1Strategic Support Force Information Engineering University, Zhengzhou 450001
    2Henan Key Laboratory of Information Security (Strategic Support Force Information Engineering University), Zhengzhou 450001
References
Share
https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/10.7544/issn1000-1239.202221034
Share to
QR

Scan QR to access full text

Cite this article
BibTeX
Citations
表12种不同金属材料的力学参数
科
Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)
属
Genus
种数
Number of
species
占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏
  • BibTeX
  • EndNote
  • RefWorks
  • TxT