[1]陈功,朱佳俊,施勇,等.基于用户鼠标行为的身份认证方法[J].常州大学学报(自然科学版),2018,30(02):69-76.[doi:10.3969/j.issn.2095-0411.2018.02.010]
　CHEN Gong,ZHU Jiajun,SHI Yong,et al.User Authentication Method Based on Mouse Dynamics[J].Journal of Changzhou University(Natural Science Edition),2018,30(02):69-76.[doi:10.3969/j.issn.2095-0411.2018.02.010]
点击复制

基于用户鼠标行为的身份认证方法()
分享到：

常州大学学报(自然科学版)[ISSN:2095-0411/CN:32-1822/N]

卷:
第30卷
期数:
2018年02期
页码:
69-76
栏目:
计算机与信息工程
出版日期:
2018-03-31

文章信息/Info

Title:
User Authentication Method Based on Mouse Dynamics
作者:
陈功1; 朱佳俊1; 2; 施勇1; 薛质1
1. 上海交通大学 网络空间安全学院,上海 200240; 2. 上海交通大学 数学科学学院,上海 200240
Author(s):
CHEN Gong1;  ZHU Jiajun1; 2;  SHI Yong1;  XUE Zhi1
1. School of Cyber Security, Shanghai Jiao Tong University, Shanghai 200240, China; 2. School of Mathematical Science, Shanghai Jiao Tong University, Shanghai 200240, China
关键词:
鼠标行为;  极限学习机;  身份认证
Keywords:
mouse dynamics;  extreme learning machine;  user authentication
分类号:
TP 309
DOI:
10.3969/j.issn.2095-0411.2018.02.010
文献标志码:
A
摘要:
提出一种基于用户鼠标行为特征的身份认证方法,通过对用户的鼠标行为数据进行分析,归纳出两类鼠标行为特征,基于鼠标基本行为的一级特征,以及基于基本行为关系的二级特征,并采用极限学习机作为分类算法实现对用户身份的认证。通过实验表明所提出的二级特征能够有效降低认证方法的认假率,而极限学习机因其良好的泛化能力与优秀的学习速度是合适的认证算法。
Abstract:
This paper presents a user authentication method based on mouse dynamics as a behavioral biometric. Two kinds of features are proposed to characterize a user’s unique pattern of the interaction with mouse device. One-level features are fine-granted metrics extracted for accurate characterization of five basic mouse actions and two-level features are defined based on the relations between the basic mouse actions. Extreme Learning Machine(ELM)is utilized for quick and efficient classification. The efficacy of the proposed features and verification method are evaluated by experiments based on a publicly available dataset. The experimental results demonstrate the high efficiency of ELM in verifying users’ identities based on mouse dynamics.

参考文献/References:

[1]MATYAS V, RIHA Z. Toward reliable user authentication through biometrics[J]. IEEE Security & Privacy Magazine, 2003, 1(3): 45-49.
[2]SHI E, NIU Y, JAKOBSSON M, et al. Implicit authentication through learning user behavior[C]// International Conference on Information Security. Berlin: Springer-Verlag, 2011: 99-113.
[3]FOUAD K M, HASSAN B M, HASSAN M F. User authentication based on dynamic keystroke recognition[J]. International Journal of Ambient Computing and Intelligence, 2016, 7(2): 1-32.
[4] MORALES A, FIERREZ J, ORTEGAGARCIA J. Towardspredicting good users for biometric recognition based on keystroke dynamics[C]// European Conference on Computer Vision Workshops. Zurich: Springer, 2016: 711-724.
[5]桑应朋. 基于计算机击键动力学的用户身份鉴别[D]. 成都: 西南交通大学, 2004.
[6]AHMED A A E, TRAORE I. Detecting computer intrusions using behavioral biometrics[C]// Conference on Privacy, Security and Trust St. Andrews: DBLP, 2005: 91-98.
[7]AHMED A A E, TRAORE I. A new biometric technology based on mouse dynamics[J]. IEEE Transactions on Dependable and Secure Computing, 2007, 4(3): 165-179.
[8]GAMBOA H. A behavioral biometric system based on human-computer interaction[J]. Proceedings of SPIE-The International Society for Optical Engineering, 2004, 5404:381-392.
[9]PUSARA M, BRODLEY C E. User re-authentication via mouse movements[C]// ACM Workshop on Visualization and Data Mining for Computer Security. New York: ACM, 2004:1-8.
[10] HASHIA S, POLLETT C, STAMP M. On using mouse movements as a biometric[C]//In Proceeding in the International Conference on Computer Science and its Applications. Singapore: ICCSA, 2005:143-147.
[11] OLIVEIRA P X, CHANNARAYAPPA V, O’DONNEL E, et al. Mouse movement biometric system[C]//Proceedings of Student-Faculty Research Day. New York: Pace University, 2013: 21-28.
[12] NAKKABI Y, TRAORE I, AHMED A A E. Improving mouse dynamics biometric performance using variance reduction via extractors with separate features[J]. IEEE Transactions on Systems, Man, and Cybernetics-Part A: Systems and Humans, 2010, 40(6):1345-1353.
[13] SHEN C, CAI Z, GUAN X, et al. User authentication through mouse dynamics[J]. IEEE Transactions on Information Forensics & Security, 2013, 8(1):16-30.
[14] ZHENG N, PALOSKI A, WANG H. An efficient user verification system using angle-based mouse movement biometrics[J]. ACM Transactions on Information and System Security, 2016, 18(3): 1-27.
[15] HUANG G B, ZHU Q Y, SIEW C K. Extreme learning machine: theory and applications[J]. Neurocomputing, 2006, 70(1): 489-501.
[16] FüL?P á, KOVáCS L, KURICS T. Balabit mouse dynamics challenge data set[EB/OL].(2017-06-20)
[2017-10-12].https://github.com/balabit/Mouse-Dynamics-Challenge.

备注/Memo

备注/Memo:
收稿日期:2017-11-10。
基金项目:国家自然科学基金资助项目(51375062,514755050); 江苏省重点研发计划项目(BE2015043)。
作者简介:陈功(1989—),男,江苏南通人,硕士生。通信联系人:薛质(1971—),E-mail: zxue@sjtu.edu.cn
更新日期/Last Update: 2018-03-20