Detecting Replay Attacks Using Multi-Channel Audio: A Neural Network-Based Method

被引:15
作者
Gong, Yuan [1 ]
Yang, Jian [1 ]
Poellabauer, Christian [1 ]
机构
[1] Univ Notre Dame, Dept Comp Sci & Engn, Notre Dame, IN 46637 USA
基金
美国国家科学基金会;
关键词
Microphone arrays; Task analysis; Feature extraction; Speech recognition; Array signal processing; Convolution; Microphone array signal processing; voice anti-spoofing; replay attack; beamforming; INSTANTANEOUS FREQUENCY; FEATURES;
D O I
10.1109/LSP.2020.2996908
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
With the rapidly growing number of security-sensitive systems that use voice as the primary input, it becomes increasingly important to address these systems' potential vulnerability to replay attacks. Previous efforts to address this concern have focused primarily on single-channel audio. In this paper, we introduce a novel neural network-based replay attack detection model that further leverages spatial information of multi-channel audio and is able to significantly improve the replay attack detection performance.
引用
收藏
页码:920 / 924
页数:5
相关论文
共 50 条
  • [41] Sparse superlayered neural network-based multi-omics cancer subtype classification
    Joshi, Prasoon
    Jeong, Seokho
    Park, Taesung
    INTERNATIONAL JOURNAL OF DATA MINING AND BIOINFORMATICS, 2020, 24 (01) : 58 - 73
  • [42] Method of radar detecting small signal based on genetic algorithm and neural network
    Lv, Q
    Li, JX
    Ma, XY
    ICEMI 2005: Conference Proceedings of the Seventh International Conference on Electronic Measurement & Instruments, Vol 4, 2005, : 390 - 395
  • [43] A Deep Learning Model for Fault Diagnosis with a Deep Neural Network and Feature Fusion on Multi-Channel Sensory Signals
    Ye, Qing
    Liu, Shaohu
    Liu, Changhua
    SENSORS, 2020, 20 (15) : 1 - 19
  • [44] Learning Representations for Neural Network-Based Classification Using the Information Bottleneck Principle
    Amjad, Rana Ali
    Geiger, Bernhard C.
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2020, 42 (09) : 2225 - 2239
  • [45] Artificial Neural Network-Based Model Predictive Control Using Correlated Data
    Hassanpour, Hesam
    Corbett, Brandon
    Mhaskar, Prashant
    INDUSTRIAL & ENGINEERING CHEMISTRY RESEARCH, 2022, 61 (08) : 3075 - 3090
  • [46] Convolutional Neural Network-Based Human Identification Using Outer Ear Images
    Sinha, Harsh
    Manekar, Raunak
    Sinha, Yash
    Ajmera, Pawan K.
    SOFT COMPUTING FOR PROBLEM SOLVING, 2019, 817 : 707 - 719
  • [47] A Novel Fingerprint Recovery Scheme using Deep Neural Network-based Learning
    Samuel Lee
    Seok-Woo Jang
    Dongho Kim
    Hernsoo Hahn
    Gye-Young Kim
    Multimedia Tools and Applications, 2021, 80 : 34121 - 34135
  • [48] Mental Disease Feature Extraction with MRI by 3D Convolutional Neural Network with Multi-Channel Input
    Cao, Lijun
    Liu, Zhi
    Cao, Yankun
    Li, Kening
    He, Xiaofu
    2016 IEEE INTERNATIONAL CONFERENCE ON SMART CLOUD (SMARTCLOUD), 2016, : 224 - 227
  • [49] Skeletal joint image-based multi-channel fusion network for human activity recognition
    Sun, Tianang
    Lian, Chao
    Dong, Fanghecong
    Shao, Jinliang
    Zhang, Xinyue
    Xiao, Qijun
    Ju, Zhongjie
    Zhao, Yuliang
    KNOWLEDGE-BASED SYSTEMS, 2025, 315
  • [50] Graph Convolutional Network-Based Method for Fault Diagnosis Using a Hybrid of Measurement and Prior Knowledge
    Chen, Zhiwen
    Xu, Jiamin
    Peng, Tao
    Yang, Chunhua
    IEEE TRANSACTIONS ON CYBERNETICS, 2022, 52 (09) : 9157 - 9169