Mining a new biometrics to improve the accuracy of keystroke dynamics-based authentication system on free-text

Cheng Jung Tsai, Kuen Jhe Shih

Research output: Contribution to journalArticle

Abstract

Related works for applying keystroke dynamics (KD) on free text identification indicated that applying KD can improve the accuracy of personal authentication on free text. As the result, this paper proposes a new biometrics, i.e., the keystroke clusters map (KC-Map), by clustering users’ keystrokes in order to effectively enhance the accuracy of personal authentication in free text. Since KC-Map is conducted via clustering, it is not suitable for traditional classifiers. In order to tackle this problem, the paper further proposes a keystroke clusters map similarity classifier (KCMS classifier). Experimental results positively show that the proposed KC-Map and KCMS classifier can efficiently improve the accuracy of personal authentication on free text with up to 1.27 times. In addition, one of the huge disadvantages on the current approaches in free text identification is that users are generally required to be trained for several months. Longer training time makes free text identification more impractical. Another motivation of this paper is to explore whether it is possible to shorten the training time into an acceptable range. Experimental results show that, to achieve relatively fair identification accuracy, users only need to carry out about 20 min for training.

Original languageEnglish
Pages (from-to)125-137
Number of pages13
JournalApplied Soft Computing Journal
Volume80
DOIs
Publication statusPublished - 2019 Jul 1

Fingerprint

Biometrics
Authentication
Classifiers

All Science Journal Classification (ASJC) codes

  • Software

Cite this

@article{6976707146204fc384a545d461f8c2a6,
title = "Mining a new biometrics to improve the accuracy of keystroke dynamics-based authentication system on free-text",
abstract = "Related works for applying keystroke dynamics (KD) on free text identification indicated that applying KD can improve the accuracy of personal authentication on free text. As the result, this paper proposes a new biometrics, i.e., the keystroke clusters map (KC-Map), by clustering users’ keystrokes in order to effectively enhance the accuracy of personal authentication in free text. Since KC-Map is conducted via clustering, it is not suitable for traditional classifiers. In order to tackle this problem, the paper further proposes a keystroke clusters map similarity classifier (KCMS classifier). Experimental results positively show that the proposed KC-Map and KCMS classifier can efficiently improve the accuracy of personal authentication on free text with up to 1.27 times. In addition, one of the huge disadvantages on the current approaches in free text identification is that users are generally required to be trained for several months. Longer training time makes free text identification more impractical. Another motivation of this paper is to explore whether it is possible to shorten the training time into an acceptable range. Experimental results show that, to achieve relatively fair identification accuracy, users only need to carry out about 20 min for training.",
author = "Tsai, {Cheng Jung} and Shih, {Kuen Jhe}",
year = "2019",
month = "7",
day = "1",
doi = "10.1016/j.asoc.2019.03.033",
language = "English",
volume = "80",
pages = "125--137",
journal = "Applied Soft Computing",
issn = "1568-4946",
publisher = "Elsevier BV",

}

Mining a new biometrics to improve the accuracy of keystroke dynamics-based authentication system on free-text. / Tsai, Cheng Jung; Shih, Kuen Jhe.

In: Applied Soft Computing Journal, Vol. 80, 01.07.2019, p. 125-137.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Mining a new biometrics to improve the accuracy of keystroke dynamics-based authentication system on free-text

AU - Tsai, Cheng Jung

AU - Shih, Kuen Jhe

PY - 2019/7/1

Y1 - 2019/7/1

N2 - Related works for applying keystroke dynamics (KD) on free text identification indicated that applying KD can improve the accuracy of personal authentication on free text. As the result, this paper proposes a new biometrics, i.e., the keystroke clusters map (KC-Map), by clustering users’ keystrokes in order to effectively enhance the accuracy of personal authentication in free text. Since KC-Map is conducted via clustering, it is not suitable for traditional classifiers. In order to tackle this problem, the paper further proposes a keystroke clusters map similarity classifier (KCMS classifier). Experimental results positively show that the proposed KC-Map and KCMS classifier can efficiently improve the accuracy of personal authentication on free text with up to 1.27 times. In addition, one of the huge disadvantages on the current approaches in free text identification is that users are generally required to be trained for several months. Longer training time makes free text identification more impractical. Another motivation of this paper is to explore whether it is possible to shorten the training time into an acceptable range. Experimental results show that, to achieve relatively fair identification accuracy, users only need to carry out about 20 min for training.

AB - Related works for applying keystroke dynamics (KD) on free text identification indicated that applying KD can improve the accuracy of personal authentication on free text. As the result, this paper proposes a new biometrics, i.e., the keystroke clusters map (KC-Map), by clustering users’ keystrokes in order to effectively enhance the accuracy of personal authentication in free text. Since KC-Map is conducted via clustering, it is not suitable for traditional classifiers. In order to tackle this problem, the paper further proposes a keystroke clusters map similarity classifier (KCMS classifier). Experimental results positively show that the proposed KC-Map and KCMS classifier can efficiently improve the accuracy of personal authentication on free text with up to 1.27 times. In addition, one of the huge disadvantages on the current approaches in free text identification is that users are generally required to be trained for several months. Longer training time makes free text identification more impractical. Another motivation of this paper is to explore whether it is possible to shorten the training time into an acceptable range. Experimental results show that, to achieve relatively fair identification accuracy, users only need to carry out about 20 min for training.

UR - http://www.scopus.com/inward/record.url?scp=85063215481&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85063215481&partnerID=8YFLogxK

U2 - 10.1016/j.asoc.2019.03.033

DO - 10.1016/j.asoc.2019.03.033

M3 - Article

AN - SCOPUS:85063215481

VL - 80

SP - 125

EP - 137

JO - Applied Soft Computing

JF - Applied Soft Computing

SN - 1568-4946

ER -