The accuracy of user authentication through keystroke features using the most frequent words

Alaa Darabseh, Akbar Siami Namin

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

4 Scopus citations

Abstract

We study the performance and inuence of various keystroke features on keystroke dynamics authentication systems. In particular, we investigate the performance of keystroke features on a subset of most frequently used English words. Four features including key duration, ight time latency, diagraph time latency, and word total time duration were analyzed using non-parametric Wilcoxon Man-Whitney statistical test technique. Two experiments were performed to measure the performance of each feature individually as well as the results from the combinations of these features. The results of the experiments were evaluated with eight users. The results show that while the combination of hold time and word total duration produces best performance among all four keystroke features combinations, hold time of the key press offers the optimal result if used independently.

Original languageEnglish
Title of host publicationProceedings of 2014 9th Annual Cyber and Information Security Research Conference, CISRC 2014
PublisherAssociation for Computing Machinery
Pages85-88
Number of pages4
ISBN (Print)9781450328128
DOIs
StatePublished - 2014
Event9th Annual Cyber and Information Security Research Conference, CISRC 2014 - Oak Ridge, TN, United States
Duration: Apr 8 2014Apr 10 2014

Publication series

NameACM International Conference Proceeding Series

Conference

Conference9th Annual Cyber and Information Security Research Conference, CISRC 2014
CountryUnited States
CityOak Ridge, TN
Period04/8/1404/10/14

Keywords

  • Authentication
  • Biometrics
  • Keystroke dynamics
  • Keystroke feature
  • Security

Fingerprint Dive into the research topics of 'The accuracy of user authentication through keystroke features using the most frequent words'. Together they form a unique fingerprint.

Cite this