MBBFAuth: Multimodal Behavioral Biometrics Fusion for Continuous Authentication on Non-Portable Devices

被引:0
|
作者
Li, Jiajia [1 ]
Yi, Qian [1 ]
Lim, Ming K. [2 ]
Yi, Shuping [1 ]
Zhu, Pengxing [1 ]
Huang, Xingjun [3 ]
机构
[1] Chongqing Univ, Coll Mech & Vehicle Engn, Chongqing 400044, Peoples R China
[2] Univ Glasgow, Adam Smith Business Sch, Glasgow G12 8QQ, Scotland
[3] Chongqing Univ Posts & Telecommun, Sch Modern Posts, Chongqing 400065, Peoples R China
基金
中国国家自然科学基金;
关键词
Authentication; Biometrics; Accuracy; Security; Feature extraction; Faces; Graphical user interfaces; Convolutional neural networks; Robustness; Monitoring; Behavioral biometrics; continuous authentication; multimodal fusion; generative adversarial network; long short-term memory; autoencoder; USER AUTHENTICATION;
D O I
10.1109/TIFS.2024.3480363
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
Continuous authentication based on behavioral biometrics is effective and crucial as user behaviors are not easily copied. However, relying solely on one behavioral biometric limits the accuracy of continuous authentication. Therefore, a continuous authentication system based on multimodal behavioral biometrics fusion is proposed in this study, which fuses three modalities: contextual behavior, mouse behavior, and information interaction behavior. The multimodal dataset of user behavior is collected through a self-built website, and the behavioral feature sets for each modality are then created. An improved generative adversarial network method is used to align the datasets of the three modalities. The autoencoder with long short-term memory is employed for unsupervised anomaly detection of time-series behaviors and enables continuous authentication for each modality. The multimodal fusion is achieved using the meta-model of the stacked generalization method, and the final decision for continuous authentication is then determined. The experimental results demonstrate that the proposed multimodal fusion method significantly outperforms the unimodal and provides an effective way to improve the accuracy and user-friendliness of continuous authentication. This study offers insights into user behavior analysis, behavioral anomaly detection, and multimodal behavior fusion.
引用
收藏
页码:10000 / 10015
页数:16
相关论文
共 44 条
  • [41] M2auth: A multimodal behavioral biometric authentication using feature-level fusion
    Mahfouz, Ahmed
    Mostafa, Hebatollah
    Mahmoud, Tarek M.
    Sharaf Eldin, Ahmed
    Neural Computing and Applications, 2024, 36 (34) : 21781 - 21799
  • [42] Validation of two handheld devices against a non-portable three-dimensional surface scanner and assessment of potential use for intraoperative facial imaging
    Koban, Konstantin Christoph
    Perko, Philipp
    Etzel, Lucas
    Li, Zhouxiao
    Schenck, Thilo Ludwig
    Giunta, Riccardo Enzo
    JOURNAL OF PLASTIC RECONSTRUCTIVE AND AESTHETIC SURGERY, 2020, 73 (01): : 141 - 148
  • [43] A novel scheme to address the fusion uncertainty in multi-modal continuous authentication schemes on mobile devices
    Smith-Creasey, Max
    Rajarajan, Muttukrishnan
    2019 INTERNATIONAL CONFERENCE ON BIOMETRICS (ICB), 2019,
  • [44] Linear and Non-Linear Multimodal Fusion for Continuous Affect Estimation in-the-Wild
    Gaus, Yona Falinie A.
    Meng, Hongying
    PROCEEDINGS 2018 13TH IEEE INTERNATIONAL CONFERENCE ON AUTOMATIC FACE & GESTURE RECOGNITION (FG 2018), 2018, : 492 - 498