自适应分数级融合的多模态生物特征认证

doi:10.19665/j.issn1001-2400.2023.04.002

摘要/Abstract

摘要：

近年来,基于生物特征的身份认证在日常生活中扮演着至关重要的角色。多模态认证方法通过融合多种生物特征对用户进行身份认证,可以提供比单模态认证更高的安全性和认证准确性。然而,现有的多模态认证方案大多采用固定参数和规则的融合策略来实现认证,无法适应不同的认证场景,从而导致次优的认证性能。针对上述问题,提出了一种基于自适应粒子群优化算法的自适应分数级融合多模态认证方案。首先,方案根据上下文信息来确定当前认证场景所需的安全等级,接着自适应地选择融合策略的规则和参数,在提供安全身份认证的同时保证系统具有最佳的认证性能。其次,对采集的多模态生物特征数据进行预处理和特征提取,再使用所选择的最优融合策略来实现身份认证。最后,在公开的数据集上对自适应分数级融合的多模态认证方案进行实验分析,结果表明所提方案在真实数据上的可行性和有效性;在相同的认证安全等级下,本方案实现了比现有方案更小的全局错误率。

关键词: 自适应, 多模态, 认证, 分数级融合, 优化算法

Abstract:

In recent years,biometric-based authentication has played a vital role in our daily life.The multi-modal authentication method by fusing multiple biometrics to authenticate users can provide a higher security and authentication accuracy than single-modal authentication.However,most of the existing multi-modal authentication schemes adopt fusion strategies with fixed rules and parameters to achieve authentication,which cannot adapt to different authentication scenarios,thus resulting in a sub-optimal authentication performance.To solve the above problems,this paper proposes an Adaptive Particle Swarm Optimization based multi-modal authentication scheme that adaptively fuses multiple biometrics at the score level.First,the proposed scheme determines the security level required for the current authentication scenario according to the context information,and then adaptively selects rules and parameters of the fusion strategy to provide secure authentication and to ensure the best authentication performance of the system.Second,the collected multi-modal biometric data after preprocessing and feature extraction is fused using the selected optimal fusion strategy to achieve authentication.Finally,experimental analyses on the public dataset demonstrate that the proposed scheme is of feasibility and effectiveness by actual data,and can achieve a smaller global error rate than existing schemes under the same authentication security requirements.

Key words: adaptive, multi-modal, authentication, score-level fusion, optimization

中图分类号:

TN915.08

姜奇,赵晓敏,赵贵川,王金花,李兴华. 自适应分数级融合的多模态生物特征认证[J]. 西安电子科技大学学报, 2023, 50(4): 11-21.

JIANG Qi,ZHAO Xiaomin,ZHAO Guichuan,WANG Jinhua,LI Xinghua. Adaptive score-level fusion for multi-modal biometric authentication[J]. Journal of Xidian University, 2023, 50(4): 11-21.

图/表 9

图1

图2

图3

表1

图4

图5

图6

图7

表2

参考文献 32

[1]	OMETOV A, PETROV S, BEZZATEEV S, et al. Challenges of Multi-Factor Authentication for Securing Advanced IoT Applications[J]. IEEE Network, 2019, 33(2):82-88.
[2]	JIANG Q, ZHANG X, ZHANG N, et al. Three-Factor Authentication Protocol Using Physical Unclonable Function for IoV[J]. Computer Communications, 2021, 173:45-55. doi: 10.1016/j.comcom.2021.03.022
[3]	JIANG Q, ZHANG N, NI J, et al. Unified Biometric Privacy Preserving Three-Factor Authentication and Key Agreement for Cloud-Assisted Autonomous Vehicles[J]. IEEE Transactions on Vehicular Technology, 2020, 69(9):9390-9401. doi: 10.1109/TVT.25
[4]	SANDIP K S M, JHA V K. Multibiometric Fusion Strategy and Its Applications:A Review[J]. Information Fusion, 2019, 49(9):174-204. doi: 10.1016/j.inffus.2018.11.018
[5]	SADHYA D, SINGH S K. Construction of A Bayesian Decision Theory-Based Secure Multimodal Fusion Framework for Soft Biometric Traits[J]. IET Biometrics, 2018, 7(3):251-259. doi: 10.1049/bme2.v7.3
[6]	GSW A, TS B, KS C, et al. Robust Multimodal Biometric System Based on Optimal Score Level Fusion Model[J]. Expert Systems with Applications, 2019, 116(2):364-376. doi: 10.1016/j.eswa.2018.08.036
[7]	DWIVEDI R, DEY S. Score-Level Fusion for Cancelable Multi-Biometric Verification[J]. Pattern Recognition Letters, 2019, 126(9):58-67. doi: 10.1016/j.patrec.2018.04.022
[8]	CAMARA C, PERIS-LOPEZ P, GONZALEZ-MANZANO L, et al. Real-Time Electrocardiogram Streams for Continuous Authentication[J]. Applied Soft Computing, 2018, 68(7):784-794. doi: 10.1016/j.asoc.2017.07.032
[9]	WU C, HE K, CHEN J, et al. Liveness is Not Enough:Enhancing Fingerprint Authentication with Behavioral Biometrics to Defeat Puppet Attacks[C]// 29th USENIX Security Symposium.Berkeley:USENIX, 2020:2219-2236.
[10]	GADALETA M, ROSSI M. IDNet Smartphone-Based Gait Recognition with Convolutional Neural Networks[J]. Pattern Recognition, 2016, 74(2):25-37. doi: 10.1016/j.patcog.2017.09.005
[11]	ROSS A, POH N. Multibiometric Systems:Overview,Case Studies and Open Issues[M]. Handbook of Remote Biometrics.Heidelberg:Springer, 2014:273-292.
[12]	ISO. Information Technology-Biometric Presentation Attack Detection-Part 3:Testing and Reporting:ISO/IEC:30107-3:2017[S/OL]. [2017-09].https://www.iso.org/standard/67381.html.
[13]	EBERZ S, PAOLETTI N, ROESCHLIN M, et al. Broken Hearted:How to Attack ECG Biometrics[C]// Network and Distributed System Security Symposium 2017(NDSS). San Diego: NDSS, 2017:1-15.
[14]	PHOHAV V, SERWADDA A. When Kids' Toys Breach Mobile Phone Security[C]// Proceedings of the 2013 ACM SIGSAC Conference on Computer and Communications Security. New York: ACM, 2013:559-610.
[15]	EBERZ S, LOVISOTTO G, PATANE A, et al. When Your Fitness Tracker Betrays You:Quantifying the Predictability of Biometric Features Across Contexts[C]// 2018 IEEE Symposium on Security and Privacy.Piscataway:IEEE, 2018:889-905.
[16]	BALA N, GUPTA R, KUMAR A. Multimodal Biometric System Based on Fusion Techniques:A Review[J]. Information Security Journal:A Global Perspective, 2022, 31(3):289-337. doi: 10.1080/19393555.2021.1974130
[17]	刘礼才, 李锐光, 殷丽华, 等. 面向移动智能设备的多特征融合隐式鉴别机制研究[J]. 电子学报, 2016, 44(11):2713-2719. doi: 10.3969/j.issn.0372-2112.2016.11.021
	LIU Licai, LI Ruiguang, YIN Lihua, et al. Research on Multi-Feature Fusion Impact Authentication for Intelligent Mobile Device[J]. Acta Electronica Sinica, 2016, 44(11):2713-2719. doi: 10.3969/j.issn.0372-2112.2016.11.021
[18]	姜奇, 文悦, 张瑞杰, 等. 面向智能手机的自适应触屏持续认证方案[J]. 电子学报, 2022, 50(5):1131-1139. doi: 10.12263/DZXB.20210624
	JIANG Qi, WEN Yue, ZHANG Ruijie, et al. An Adaptive Touchscreen Based Continuous Authentication Scheme for Smart Phones[J]. Acta Electronica Sinica, 2022, 50(5):1131-1139. doi: 10.12263/DZXB.20210624
[19]	KHODADOUST J, MEDINA-PEREZ M A, MONROY R, et al. A Multibiometric System Based on the Fusion of Fingerprint,Finger-Vein,and Finger-Knuckle-Print[J]. Expert Systems with Applications, 2021, 176:114687. doi: 10.1016/j.eswa.2021.114687
[20]	AIZI K, OUSLIM M. Score Level Fusion in Multi-Biometric Identification Based on Zones of Interest[J]. Journal of King Saud University-Computer and Information Sciences, 2022, 34(1):1498-1509.
[21]	PUROHIT H, AJMERA P K. Optimal Feature Level Fusion for Secured Human Authentication in Multimodal Biometric System[J]. Machine Vision and Applications, 2021, 32(1):1-12. doi: 10.1007/s00138-020-01119-9
[22]	SITOVAZ, SEDENKA J, YANG Q, et al. HMOG:New Behavioral Biometric Features for Continuous Authentication of Smartphone Users[J]. IEEE Transactions on Information Forensics and Security, 2016, 11(5):877-892. doi: 10.1109/TIFS.2015.2506542
[23]	HANMANDLU M, GROVER J, GUREJA A, et al. Score Level Fusion of Multimodal Biometrics Using Triangular Norms[J]. Pattern Recognition Letters, 2011, 32(14):1843-1850. doi: 10.1016/j.patrec.2011.06.029
[24]	VEERAMACHANENI K K, OSADCIW L A, VARSHNEY P K. An Adaptive Multimodal Biometric Management Algorithm[J]. IEEE Transactions on Systems,Man and Cybernetics, 2005, 35(3):344-356.
[25]	KUMAR A, KANHANGAD V, ZHANG D. A New Framework for Adaptive Multimodal Biometrics Management[J]. IEEE Transactions on Information Forensics and Security, 2010, 5(1):92-102. doi: 10.1109/TIFS.2009.2031892
[26]	SINGH M, SINGH R, ROSS A. A Comprehensive Overview of Biometric Fusion[J]. Information Fusion, 2019, 52:187-205. doi: 10.1016/j.inffus.2018.12.003
[27]	VATSA M, R SINGH, NOORE A, et al. On the Dynamic Selection of Biometric Fusion Algorithms[J]. IEEE Transactions on Information Forensics and Security, 2010, 5(3):470-479. doi: 10.1109/TIFS.2010.2056683
[28]	EDWARDS T, HOSSAIN M S. Effectiveness of Deep Learning on Serial Fusion Based Biometric Systems[J]. IEEE Transactions on Artificial Intelligence, 2021, 2(1):28-41. doi: 10.1109/TAI.2021.3064003
[29]	WALIA G S, SINGH T, SINGH K, et al. Robust Multimodal Biometric System Based on Optimal Score Level Fusion Model[J]. Expert Systems with Applications, 2019, 116(2):364-376. doi: 10.1016/j.eswa.2018.08.036
[30]	ALAGARSAMY S B, MURUGAN K. Multimodal of Ear and Face Biometric Recognition Using Adaptive Approach Runge-Kutta Threshold Segmentation and Classifier with Score Level Fusion[J]. Wireless Personal Communications, 2022, 124(2):1061-1080. doi: 10.1007/s11277-021-09394-z
[31]	ZHANZ H, ZHANG J, LI Y, et al. Adaptive Particle Swarm Optimization[J]. IEEE Transactions on Systems,Man,and Cybernetics, 2009, 39(6):1362-1381.
[32]	YANG Q, PENG G, NGUYEN D T, et al. A Multimodal Data Set for Evaluating Continuous Authentication Performance in Smartphones[C]// Proceedings of the 12th ACM Conference on Embedded Network Sensor Systems. New York: ACM, 2014:358-359.

安全等级	融合规则	融合参数	决策阈值	全局错误率
0				0
0.1	Exp	(0.282 9,0.288 6)	0.952 6	0.009 7
0.2	Exp	(0.114 0,0.131 2)	0.418 1	0.017 1
0.3	Exp	(0.4224,0.490 9)	1.625 0	0.024 7
0.4	Exp	(0.279 1,0.317 2)	1.097 0	0.031 5
0.5	Exp	(0.293 2,0.332 5)	1.151 3	0.037 1
0.6	Schweizer	(0.848 3)	0.011 0	0.039 0
0.7	Schweizer	(1.028 1)	0.409 1	0.047 1
0.8	Frank	(1.306 8)	0.041 3	0.046 5
0.9	Schweizer	(1.066 1)	0.223 7	0.044 0
1.0	Frank	(0.781 4)	0.127 6	0.046 6
1.1	Schweizer	(1.349 1)	0.299 6	0.045 7
1.2	Einstein product		0.186 9	0.049 1
1.3	Yager	(0.671 8)	0.027 0	0.047 9
1.4	Yager	(0.314 7)	0.004 0	0.035 3
1.5	Frank	(1.262 5)	0.679 2	0.032 6
1.6	Yager	(0.296 5)	0.013 5	0.027 2
1.7	Yager	(0.269 2)	0.054 2	0.022 8
1.8	Schweizer	(4.570 4)	0.743 2	0.017 4
1.9	Frank	(1.659 2)	0.890 7	0.011 3
2.0				0

方案	认证时间/ms	算法时间/s
文献[24]	0.012	粒子群优化算法	197.337
文献[25]	0.011
文中方案	0.007	自适应粒子群优化算法	394.315