An embedded system for extracting keystroke patterns using pressure sensors

Christopher S. Leberknight, Michael L. Recce

Research output: Contribution to journalArticle

Abstract

Popular biometric security technologies include fingerprint and iris recognition systems. These technologies are extremely accurate because the patterns associated with an individual's finger or eye are very unique and static. However, when these technologies are used for physical access control they inform the potential adversary that specific characteristics are required to gain access. Behaviometrics aims to develop new strategies to enhance physical security via covert monitoring of distinct behavioral patterns. This research presents a novel stand-alone behaviometric prototype that incorporates standard password security with unique pressure characteristics to covertly analyse individual typing patterns. The prototype is evaluated under a controlled setting with 62 human subjects and nine classification algorithms. The kNN algorithm produced the highest classification rate of 94%. This research is one of the few papers that empirically substantiates biometric performance with a large-scale human subject trial, and also identifies several critical design considerations that impact classifier performance.

Original languageEnglish
Pages (from-to)249-270
Number of pages22
JournalInternational Journal of Biometrics
Volume7
Issue number3
DOIs
StatePublished - 1 Jan 2015

Fingerprint

Pressure Sensor
Pressure sensors
Embedded systems
Embedded Systems
Biometrics
Prototype
Fingerprint Recognition
Iris Recognition
Password
Classification Algorithm
Access Control
Access control
Classifiers
Classifier
Monitoring
Distinct
Human

Keywords

  • Biometrics
  • Classification
  • Keystroke analysis
  • Pattern recognition
  • Physical security
  • Typing dynamics

Cite this

@article{e4873ad753b74f349b1fe0f3a405a9bb,
title = "An embedded system for extracting keystroke patterns using pressure sensors",
abstract = "Popular biometric security technologies include fingerprint and iris recognition systems. These technologies are extremely accurate because the patterns associated with an individual's finger or eye are very unique and static. However, when these technologies are used for physical access control they inform the potential adversary that specific characteristics are required to gain access. Behaviometrics aims to develop new strategies to enhance physical security via covert monitoring of distinct behavioral patterns. This research presents a novel stand-alone behaviometric prototype that incorporates standard password security with unique pressure characteristics to covertly analyse individual typing patterns. The prototype is evaluated under a controlled setting with 62 human subjects and nine classification algorithms. The kNN algorithm produced the highest classification rate of 94{\%}. This research is one of the few papers that empirically substantiates biometric performance with a large-scale human subject trial, and also identifies several critical design considerations that impact classifier performance.",
keywords = "Biometrics, Classification, Keystroke analysis, Pattern recognition, Physical security, Typing dynamics",
author = "Leberknight, {Christopher S.} and Recce, {Michael L.}",
year = "2015",
month = "1",
day = "1",
doi = "10.1504/IJBM.2015.071948",
language = "English",
volume = "7",
pages = "249--270",
journal = "International Journal of Biometrics",
issn = "1755-8301",
publisher = "Inderscience Enterprises Ltd.",
number = "3",

}

An embedded system for extracting keystroke patterns using pressure sensors. / Leberknight, Christopher S.; Recce, Michael L.

In: International Journal of Biometrics, Vol. 7, No. 3, 01.01.2015, p. 249-270.

Research output: Contribution to journalArticle

TY - JOUR

T1 - An embedded system for extracting keystroke patterns using pressure sensors

AU - Leberknight, Christopher S.

AU - Recce, Michael L.

PY - 2015/1/1

Y1 - 2015/1/1

N2 - Popular biometric security technologies include fingerprint and iris recognition systems. These technologies are extremely accurate because the patterns associated with an individual's finger or eye are very unique and static. However, when these technologies are used for physical access control they inform the potential adversary that specific characteristics are required to gain access. Behaviometrics aims to develop new strategies to enhance physical security via covert monitoring of distinct behavioral patterns. This research presents a novel stand-alone behaviometric prototype that incorporates standard password security with unique pressure characteristics to covertly analyse individual typing patterns. The prototype is evaluated under a controlled setting with 62 human subjects and nine classification algorithms. The kNN algorithm produced the highest classification rate of 94%. This research is one of the few papers that empirically substantiates biometric performance with a large-scale human subject trial, and also identifies several critical design considerations that impact classifier performance.

AB - Popular biometric security technologies include fingerprint and iris recognition systems. These technologies are extremely accurate because the patterns associated with an individual's finger or eye are very unique and static. However, when these technologies are used for physical access control they inform the potential adversary that specific characteristics are required to gain access. Behaviometrics aims to develop new strategies to enhance physical security via covert monitoring of distinct behavioral patterns. This research presents a novel stand-alone behaviometric prototype that incorporates standard password security with unique pressure characteristics to covertly analyse individual typing patterns. The prototype is evaluated under a controlled setting with 62 human subjects and nine classification algorithms. The kNN algorithm produced the highest classification rate of 94%. This research is one of the few papers that empirically substantiates biometric performance with a large-scale human subject trial, and also identifies several critical design considerations that impact classifier performance.

KW - Biometrics

KW - Classification

KW - Keystroke analysis

KW - Pattern recognition

KW - Physical security

KW - Typing dynamics

UR - http://www.scopus.com/inward/record.url?scp=84942855018&partnerID=8YFLogxK

U2 - 10.1504/IJBM.2015.071948

DO - 10.1504/IJBM.2015.071948

M3 - Article

AN - SCOPUS:84942855018

VL - 7

SP - 249

EP - 270

JO - International Journal of Biometrics

JF - International Journal of Biometrics

SN - 1755-8301

IS - 3

ER -