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
  • [21] Side-Scan Sonar Image Segmentation Based on Multi-Channel Fusion Convolution Neural Networks
    Wang, Zhen
    Guo, Jianxin
    Huang, Wenzhun
    Zhang, Shanwen
    IEEE SENSORS JOURNAL, 2022, 22 (06) : 5911 - 5928
  • [22] Audio Data Mining Using Multi-perceptron Artificial Neural Network
    Shetty, Surendra
    Achary, K. K.
    INTERNATIONAL JOURNAL OF COMPUTER SCIENCE AND NETWORK SECURITY, 2008, 8 (10): : 224 - 229
  • [23] 3DSleepNet: A Multi-Channel Bio-Signal Based Sleep Stages Classification Method Using Deep Learning
    Ji, Xiaopeng
    Li, Yan
    Wen, Peng
    IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING, 2023, 31 : 3513 - 3523
  • [24] Learning One Class Representations for Face Presentation Attack Detection Using Multi-Channel Convolutional Neural Networks
    George, Anjith
    Marcel, Sebastien
    IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, 2021, 16 : 361 - 375
  • [25] An improved multi-channel and multi-scale domain adversarial neural network for fault diagnosis of the rolling bearing
    Jin, Yongze
    Song, Xiaohao
    Yang, Yanxi
    Hei, Xinhong
    Feng, Nan
    Yang, Xubo
    CONTROL ENGINEERING PRACTICE, 2025, 154
  • [26] A multi-division convolutional neural network-based plant identification system
    Turkoglu, Muammer
    Aslan, Muzaffer
    Ari, Ali
    Alcin, Zeynep Mine
    Hanbay, Davut
    PEERJ COMPUTER SCIENCE, 2021,
  • [27] An Ensemble of Deep Recurrent Neural Networks for Detecting IoT Cyber Attacks Using Network Traffic
    Saharkhizan, Mahdis
    Azmoodeh, Amin
    Dehghantanha, Ali
    Choo, Kim-Kwang Raymond
    Parizi, Reza M.
    IEEE INTERNET OF THINGS JOURNAL, 2020, 7 (09): : 8852 - 8859
  • [28] A Deep Neural Network-Based Spike Sorting With Improved Channel Selection and Artefact Removal
    Okreghe, Christian O.
    Zamani, Majid
    Demosthenous, Andreas
    IEEE ACCESS, 2023, 11 : 15131 - 15143
  • [29] Multi-View Fusion Network-Based Gesture Recognition Using sEMG Data
    Li, Gongfa
    Zou, Cejing
    Jiang, Guozhang
    Jiang, Du
    Yun, Juntong
    Zhao, Guojun
    Cheng, Yangwei
    IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS, 2024, 28 (08) : 4432 - 4443
  • [30] Wear indicator construction of rolling bearings based on multi-channel deep convolutional neural network with exponentially decaying learning rate
    She, Daoming
    Jia, Minping
    MEASUREMENT, 2019, 135 : 368 - 375