Thesis Details

Dynamic Template Adjustment in Continuous Keystroke Dynamics

Master's Thesis Student: Kulich Martin Academic Year: 2014/2015 Supervisor: Drahanský Martin, prof. Ing., Dipl.-Ing., Ph.D.
Czech title
Dynamic Template Adjustment in Continuous Keystroke Dynamics
Language
English
Abstract
Keystroke dynamics is one of behavioural biometric characteristics which can be employed for continuous user authentication. As typing style on a keyboard changes in time, the template adapting is necessary. No study covered this topic yet, as far as the author knows. This master thesis tries to fill this gap. Several classification techniques were exercised with help of keystroke data from 22 volunteers in order to test if they can be improved to unsupervised online classifiers. A significant improvement in impostor recognition was noted at one-class statistical classifier based on normed Euclidean distance. The impostor could make 23.7 % actions less than in offline version on average but the improvement was obseved with all test sets. In contrary, the genuine user recognition varied from user to user but it still kept at acceptable values.
Keywords

continuous authentication, online learning, keystroke dynamics, behavioural biometrics, machine learning, classification

Department
Degree Programme
Information Technology, Field of Study Information Technology Security
Files
Status
defended, grade C
Date
19 June 2015
Reviewer
Committee
Hanáček Petr, doc. Dr. Ing. (DITS FIT BUT), předseda
Balík Miroslav, Ing., Ph.D. (FIT CTU), člen
Burget Radek, doc. Ing., Ph.D. (DIFS FIT BUT), člen
Drábek Vladimír, doc. Ing., CSc. (DCSY FIT BUT), člen
Holík Lukáš, doc. Mgr., Ph.D. (DITS FIT BUT), člen
Matoušek Petr, doc. Ing., Ph.D., M.A. (DIFS FIT BUT), člen
Citation
KULICH, Martin. Dynamic Template Adjustment in Continuous Keystroke Dynamics. Brno, 2015. Master's Thesis. Brno University of Technology, Faculty of Information Technology. 2015-06-19. Supervised by Drahanský Martin. Available from: https://www.fit.vut.cz/study/thesis/17918/
BibTeX
@mastersthesis{FITMT17918,
    author = "Martin Kulich",
    type = "Master's thesis",
    title = "Dynamic Template Adjustment in Continuous Keystroke Dynamics",
    school = "Brno University of Technology, Faculty of Information Technology",
    year = 2015,
    location = "Brno, CZ",
    language = "english",
    url = "https://www.fit.vut.cz/study/thesis/17918/"
}
Back to top