On the discriminability of keystroke feature vectors used in fixed text keystroke authentication

Kiran S. Balagani, Vir V. Phoha, Asok Ray, Shashi Phoha

Research output: Contribution to journalArticle

31 Citations (Scopus)

Abstract

Heterogeneous and aggregate vectors are the two widely used feature vectors in fixed text keystroke authentication. In this paper, we address the question "Which vectors, heterogeneous, aggregate, or a combination of both, are more discriminative and why?" We accomplish this in three ways - (1) by providing an intuitive example to illustrate how aggregation of features inherently reduces discriminability; (2) by formulating " discriminability" as a non-parametric estimate of Bhattacharya distance, we show theoretically that the discriminability of a heterogeneous vector is higher than an aggregate vector; and (3) by conducting user recognition experiments using a dataset containing keystrokes from 33 users typing a 32-character reference text, we empirically validate our theoretical analysis. To compare the discriminability of heterogeneous and aggregate vectors with different combinations of keystroke features, we conduct feature selection analysis using three methods: (1) ReliefF, (2) correlation based feature selection, and (3) consistency based feature selection. Results of feature selection analysis reinforce the findings of our theoretical analysis.

Original languageEnglish (US)
Pages (from-to)1070-1080
Number of pages11
JournalPattern Recognition Letters
Volume32
Issue number7
DOIs
StatePublished - May 1 2011

Fingerprint

Authentication
Feature extraction
Agglomeration
Experiments

All Science Journal Classification (ASJC) codes

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Cite this

@article{789e89aa5f0d40279b8a26473a843930,
title = "On the discriminability of keystroke feature vectors used in fixed text keystroke authentication",
abstract = "Heterogeneous and aggregate vectors are the two widely used feature vectors in fixed text keystroke authentication. In this paper, we address the question {"}Which vectors, heterogeneous, aggregate, or a combination of both, are more discriminative and why?{"} We accomplish this in three ways - (1) by providing an intuitive example to illustrate how aggregation of features inherently reduces discriminability; (2) by formulating {"} discriminability{"} as a non-parametric estimate of Bhattacharya distance, we show theoretically that the discriminability of a heterogeneous vector is higher than an aggregate vector; and (3) by conducting user recognition experiments using a dataset containing keystrokes from 33 users typing a 32-character reference text, we empirically validate our theoretical analysis. To compare the discriminability of heterogeneous and aggregate vectors with different combinations of keystroke features, we conduct feature selection analysis using three methods: (1) ReliefF, (2) correlation based feature selection, and (3) consistency based feature selection. Results of feature selection analysis reinforce the findings of our theoretical analysis.",
author = "Balagani, {Kiran S.} and Phoha, {Vir V.} and Asok Ray and Shashi Phoha",
year = "2011",
month = "5",
day = "1",
doi = "10.1016/j.patrec.2011.02.014",
language = "English (US)",
volume = "32",
pages = "1070--1080",
journal = "Pattern Recognition Letters",
issn = "0167-8655",
publisher = "Elsevier",
number = "7",

}

On the discriminability of keystroke feature vectors used in fixed text keystroke authentication. / Balagani, Kiran S.; Phoha, Vir V.; Ray, Asok; Phoha, Shashi.

In: Pattern Recognition Letters, Vol. 32, No. 7, 01.05.2011, p. 1070-1080.

Research output: Contribution to journalArticle

TY - JOUR

T1 - On the discriminability of keystroke feature vectors used in fixed text keystroke authentication

AU - Balagani, Kiran S.

AU - Phoha, Vir V.

AU - Ray, Asok

AU - Phoha, Shashi

PY - 2011/5/1

Y1 - 2011/5/1

N2 - Heterogeneous and aggregate vectors are the two widely used feature vectors in fixed text keystroke authentication. In this paper, we address the question "Which vectors, heterogeneous, aggregate, or a combination of both, are more discriminative and why?" We accomplish this in three ways - (1) by providing an intuitive example to illustrate how aggregation of features inherently reduces discriminability; (2) by formulating " discriminability" as a non-parametric estimate of Bhattacharya distance, we show theoretically that the discriminability of a heterogeneous vector is higher than an aggregate vector; and (3) by conducting user recognition experiments using a dataset containing keystrokes from 33 users typing a 32-character reference text, we empirically validate our theoretical analysis. To compare the discriminability of heterogeneous and aggregate vectors with different combinations of keystroke features, we conduct feature selection analysis using three methods: (1) ReliefF, (2) correlation based feature selection, and (3) consistency based feature selection. Results of feature selection analysis reinforce the findings of our theoretical analysis.

AB - Heterogeneous and aggregate vectors are the two widely used feature vectors in fixed text keystroke authentication. In this paper, we address the question "Which vectors, heterogeneous, aggregate, or a combination of both, are more discriminative and why?" We accomplish this in three ways - (1) by providing an intuitive example to illustrate how aggregation of features inherently reduces discriminability; (2) by formulating " discriminability" as a non-parametric estimate of Bhattacharya distance, we show theoretically that the discriminability of a heterogeneous vector is higher than an aggregate vector; and (3) by conducting user recognition experiments using a dataset containing keystrokes from 33 users typing a 32-character reference text, we empirically validate our theoretical analysis. To compare the discriminability of heterogeneous and aggregate vectors with different combinations of keystroke features, we conduct feature selection analysis using three methods: (1) ReliefF, (2) correlation based feature selection, and (3) consistency based feature selection. Results of feature selection analysis reinforce the findings of our theoretical analysis.

UR - http://www.scopus.com/inward/record.url?scp=79952697017&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79952697017&partnerID=8YFLogxK

U2 - 10.1016/j.patrec.2011.02.014

DO - 10.1016/j.patrec.2011.02.014

M3 - Article

VL - 32

SP - 1070

EP - 1080

JO - Pattern Recognition Letters

JF - Pattern Recognition Letters

SN - 0167-8655

IS - 7

ER -