Continuous User Authentication using Keystroke Dynamics for Touch Devices

被引:1
作者
Herath, H. M. C. K. B. [1 ]
Dulanga, K. G. C. [1 ]
Tharindu, N. V. D. [1 ]
Ganegoda, G. U. [1 ]
机构
[1] Univ Moratuwa, Fac Informat Technol, Moratuwa, Sri Lanka
来源
2022 2ND INTERNATIONAL CONFERENCE ON IMAGE PROCESSING AND ROBOTICS (ICIPROB) | 2022年
关键词
keystroke dynamics; user authentication; touch devices;
D O I
10.1109/ICIPRob54042.2022.9798728
中图分类号
TP24 [机器人技术];
学科分类号
080202 ; 1405 ;
摘要
An authenticate users have increased due to failures in traditional authentication systems. Keystroke dynamicsbased authentication is one of the most secure behavioral biometric authentication systems. This study aims to research and implement a non-fool proof, low-cost continuous authentication system for touch devices based on keystroke dynamics. A custom-developed mobile application was used to collect users' keystroke dynamics. Bigrams were used as input parameters. 2 artificial neural networks were used in this study. The first network was used to identify users' handedness, while the second one decided to use validity. Also, input was not limited, and users could type free text. As a result, overall accuracy was above 83.74%. Based on the results, we concluded that keystroke dynamics could be used for continuous user authentication purposes even with freely typed tests.
引用
收藏
页数:6
相关论文
共 9 条
[1]  
Clarke S. F. B. L. P. R. N.L., SUBSCRIBER SUTHENTIC
[2]  
Kim P. K. J, 2018, SCH IND MANAGEMENT E
[3]  
Lin D, 2007, COMPUTER ACCESS AUTH
[4]  
Lin J.-C. L. a. K.-Y. L. C.-H., 2018, NEURAL NETWORKS BIOM
[5]  
Maiorana E., 2011, P 2011 ACM S APPL CO, P21
[6]  
Pavaday N., 2007, AFRICON 2007, P1
[7]  
Revett M. H. M. D. S. K., 2010, AUTHENTICATING COMPU
[8]  
Trojahn M., 2013, INT C MOB SERV RES U
[9]  
Upadhyaya H. C. a. S, 2017, SENSITIVITY ANAL KEY