Age and Gender as Cyber Attribution Features in Keystroke Dynamic-Based User Classification Processes
Keystroke dynamics are used to authenticate users, to reveal some of their inherent or acquired characteristics and to assess their mental and physical states. The most common features utilized are the time intervals that the keys remain pressed and the time intervals that are required to use two co...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-03-01
|
Series: | Electronics |
Subjects: | |
Online Access: | https://www.mdpi.com/2079-9292/10/7/835 |
id |
doaj-f0c4e20a694843a8b4cb373ad2b41845 |
---|---|
record_format |
Article |
spelling |
doaj-f0c4e20a694843a8b4cb373ad2b418452021-03-31T23:04:53ZengMDPI AGElectronics2079-92922021-03-011083583510.3390/electronics10070835Age and Gender as Cyber Attribution Features in Keystroke Dynamic-Based User Classification ProcessesIoannis Tsimperidis0Cagatay Yucel1Vasilios Katos2Department of Electrical and Computer Engineering, School of Engineering, Democritus University of Thrace, 67100 Xanthi, GreeceDepartment of Computing and Informatics, Bournemouth University, Poole BH12 5BB, UKDepartment of Computing and Informatics, Bournemouth University, Poole BH12 5BB, UKKeystroke dynamics are used to authenticate users, to reveal some of their inherent or acquired characteristics and to assess their mental and physical states. The most common features utilized are the time intervals that the keys remain pressed and the time intervals that are required to use two consecutive keys. This paper examines which of these features are the most important and how utilization of these features can lead to better classification results. To achieve this, an existing dataset consisting of 387 logfiles is used, five classifiers are exploited and users are classified by gender and age. The results, while demonstrating the application of these two characteristics jointly on classifiers with high accuracy, answer the question of which keystroke dynamics features are more appropriate for classification with common classifiers.https://www.mdpi.com/2079-9292/10/7/835keystroke dynamicsdata mininguser classificationfeature selectionfeature comparison |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Ioannis Tsimperidis Cagatay Yucel Vasilios Katos |
spellingShingle |
Ioannis Tsimperidis Cagatay Yucel Vasilios Katos Age and Gender as Cyber Attribution Features in Keystroke Dynamic-Based User Classification Processes Electronics keystroke dynamics data mining user classification feature selection feature comparison |
author_facet |
Ioannis Tsimperidis Cagatay Yucel Vasilios Katos |
author_sort |
Ioannis Tsimperidis |
title |
Age and Gender as Cyber Attribution Features in Keystroke Dynamic-Based User Classification Processes |
title_short |
Age and Gender as Cyber Attribution Features in Keystroke Dynamic-Based User Classification Processes |
title_full |
Age and Gender as Cyber Attribution Features in Keystroke Dynamic-Based User Classification Processes |
title_fullStr |
Age and Gender as Cyber Attribution Features in Keystroke Dynamic-Based User Classification Processes |
title_full_unstemmed |
Age and Gender as Cyber Attribution Features in Keystroke Dynamic-Based User Classification Processes |
title_sort |
age and gender as cyber attribution features in keystroke dynamic-based user classification processes |
publisher |
MDPI AG |
series |
Electronics |
issn |
2079-9292 |
publishDate |
2021-03-01 |
description |
Keystroke dynamics are used to authenticate users, to reveal some of their inherent or acquired characteristics and to assess their mental and physical states. The most common features utilized are the time intervals that the keys remain pressed and the time intervals that are required to use two consecutive keys. This paper examines which of these features are the most important and how utilization of these features can lead to better classification results. To achieve this, an existing dataset consisting of 387 logfiles is used, five classifiers are exploited and users are classified by gender and age. The results, while demonstrating the application of these two characteristics jointly on classifiers with high accuracy, answer the question of which keystroke dynamics features are more appropriate for classification with common classifiers. |
topic |
keystroke dynamics data mining user classification feature selection feature comparison |
url |
https://www.mdpi.com/2079-9292/10/7/835 |
work_keys_str_mv |
AT ioannistsimperidis ageandgenderascyberattributionfeaturesinkeystrokedynamicbaseduserclassificationprocesses AT cagatayyucel ageandgenderascyberattributionfeaturesinkeystrokedynamicbaseduserclassificationprocesses AT vasilioskatos ageandgenderascyberattributionfeaturesinkeystrokedynamicbaseduserclassificationprocesses |
_version_ |
1724177098303602688 |