The IRMA Community
Newsletters
Research IRM
Click a keyword to search titles using our InfoSci-OnDemand powered search:
|
A Keystroke Biometric System for Long-Text Input
Abstract
A novel keystroke biometric system for long-text input was developed and evaluated for user identification and authentication applications. The system consists of a Java applet to collect raw keystroke data over the Internet, a feature extractor, and pattern classifiers to make identification or authentication decisions. Experiments on more than 100 participants investigated two input modes—copy and free-text—and two keyboard types—desktop and laptop. The system can accurately identify or authenticate individuals if the same type of keyboard is used to produce the enrollment and questioned input samples. Longitudinal experiments quantified performance degradation over intervals of several weeks and two years. Additional experiments investigated the system’s hierarchical model, parameter settings, assumptions, and sufficiency of enrollment samples and input-text length. Although evaluated on input texts up to 650 keystrokes, the authors found that input of 300 keystrokes, roughly four lines of text, is sufficient for the important applications described.
Related Content
Jeff Mangers, Christof Oberhausen, Meysam Minoufekr, Peter Plapper.
© 2020.
26 pages.
|
Sylvain Maechler, Jean-Christophe Graz.
© 2020.
27 pages.
|
Sabrina Petersohn, Sophie Biesenbender, Christoph Thiedig.
© 2020.
41 pages.
|
Jonas Lundsten, Jesper Mayntz Paasch.
© 2020.
21 pages.
|
Justus Alexander Baron.
© 2020.
31 pages.
|
Vasileios Mavroeidis, Petros E. Maravelakis, Katarzyna Tarnawska.
© 2020.
19 pages.
|
Hiam Serhan, Doudja Saïdi-Kabeche.
© 2020.
30 pages.
|
|
|