Capturing cognitive fingerprints from keystroke dynamics

J. Morris Chang; Chi Chen Fang; Kuan Hsing Ho; Norene Kelly; Pei Yuan Wu; Yixiao Ding; Chris Chu; Stephen Gilbert; Amed E. Kamal; Sun Yuan Kung

doi:10.1109/MITP.2013.52

Capturing cognitive fingerprints from keystroke dynamics

J. Morris Chang, Chi Chen Fang, Kuan Hsing Ho, Norene Kelly, Pei Yuan Wu, Yixiao Ding, Chris Chu, Stephen Gilbert, Amed E. Kamal, Sun Yuan Kung

Research output: Contribution to journal › Article › peer-review

18 Scopus citations

Abstract

Conventional authentication systems identify a user only at the entry point. Keystroke dynamics can continuously authenticate users by their typing rhythms without extra devices. This article presents a new feature called cognitive typing rhythm (CTR) to continuously verify the identities of computer users. Two machine techniques, SVM and KRR, have been developed for the system. The best results from experiments conducted with 1,977 users show a false-rejection rate of 0.7 percent and a false-acceptance rate of 5.5 percent. CTR therefore constitutes a cognitive fingerprint for continuous. Its effectiveness has been verified through a large-scale dataset. This article is part of a special issue on security.

Original language	English (US)
Article number	6544526
Pages (from-to)	24-28
Number of pages	5
Journal	IT Professional
Volume	15
Issue number	4
DOIs	https://doi.org/10.1109/MITP.2013.52
State	Published - 2013

All Science Journal Classification (ASJC) codes

Software
Hardware and Architecture
Computer Science Applications

Keywords

continuous authentication
information technology
keystroke dynamics
security

Access to Document

10.1109/MITP.2013.52

Cite this

@article{7c613e25be9c4a04923b0b6068066d75,

title = "Capturing cognitive fingerprints from keystroke dynamics",

abstract = "Conventional authentication systems identify a user only at the entry point. Keystroke dynamics can continuously authenticate users by their typing rhythms without extra devices. This article presents a new feature called cognitive typing rhythm (CTR) to continuously verify the identities of computer users. Two machine techniques, SVM and KRR, have been developed for the system. The best results from experiments conducted with 1,977 users show a false-rejection rate of 0.7 percent and a false-acceptance rate of 5.5 percent. CTR therefore constitutes a cognitive fingerprint for continuous. Its effectiveness has been verified through a large-scale dataset. This article is part of a special issue on security.",

keywords = "continuous authentication, information technology, keystroke dynamics, security",

author = "Chang, {J. Morris} and Fang, {Chi Chen} and Ho, {Kuan Hsing} and Norene Kelly and Wu, {Pei Yuan} and Yixiao Ding and Chris Chu and Stephen Gilbert and Kamal, {Amed E.} and Kung, {Sun Yuan}",

year = "2013",

doi = "10.1109/MITP.2013.52",

language = "English (US)",

volume = "15",

pages = "24--28",

journal = "IT Professional",

issn = "1520-9202",

publisher = "IEEE Computer Society",

number = "4",

}

TY - JOUR

T1 - Capturing cognitive fingerprints from keystroke dynamics

AU - Chang, J. Morris

AU - Fang, Chi Chen

AU - Ho, Kuan Hsing

AU - Kelly, Norene

AU - Wu, Pei Yuan

AU - Ding, Yixiao

AU - Chu, Chris

AU - Gilbert, Stephen

AU - Kamal, Amed E.

AU - Kung, Sun Yuan

PY - 2013

Y1 - 2013

N2 - Conventional authentication systems identify a user only at the entry point. Keystroke dynamics can continuously authenticate users by their typing rhythms without extra devices. This article presents a new feature called cognitive typing rhythm (CTR) to continuously verify the identities of computer users. Two machine techniques, SVM and KRR, have been developed for the system. The best results from experiments conducted with 1,977 users show a false-rejection rate of 0.7 percent and a false-acceptance rate of 5.5 percent. CTR therefore constitutes a cognitive fingerprint for continuous. Its effectiveness has been verified through a large-scale dataset. This article is part of a special issue on security.

AB - Conventional authentication systems identify a user only at the entry point. Keystroke dynamics can continuously authenticate users by their typing rhythms without extra devices. This article presents a new feature called cognitive typing rhythm (CTR) to continuously verify the identities of computer users. Two machine techniques, SVM and KRR, have been developed for the system. The best results from experiments conducted with 1,977 users show a false-rejection rate of 0.7 percent and a false-acceptance rate of 5.5 percent. CTR therefore constitutes a cognitive fingerprint for continuous. Its effectiveness has been verified through a large-scale dataset. This article is part of a special issue on security.

KW - continuous authentication

KW - information technology

KW - keystroke dynamics

KW - security

UR - http://www.scopus.com/inward/record.url?scp=84883285664&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84883285664&partnerID=8YFLogxK

U2 - 10.1109/MITP.2013.52

DO - 10.1109/MITP.2013.52

M3 - Article

AN - SCOPUS:84883285664

SN - 1520-9202

VL - 15

SP - 24

EP - 28

JO - IT Professional

JF - IT Professional

IS - 4

M1 - 6544526

ER -

Capturing cognitive fingerprints from keystroke dynamics

Abstract

All Science Journal Classification (ASJC) codes

Keywords

Access to Document

Other files and links

Fingerprint

Cite this