TouchWB : Touch behavioral user authentication based on web browsing on smartphones

Weizhi Meng, Yu Wang*, Duncan S. Wong, Sheng Wen, Yang Xiang

*Corresponding author for this work

Research output: Contribution to journalJournal articleResearchpeer-review

Abstract

Modern mobile devices especially smartphones have rapidly evolved and are widely adopted by people of different ages. Smartphones can assist users in a variety of activities, i.e., from social networking to online shopping, but also have become an attractive target for cyber-criminals due to the stored personal data and sensitive information. The traditional authentication mechanisms like PIN suffer from well-known limitations and drawbacks in the security community; thus, touch behavioral authentication has recently received much attention. Intuitively, authentication based on free touches would be hard to build a stand-alone system. In this work, we advocate that such authentication can consider users’ actions under certain phone applications like web browser, and then propose a touch gesture-based authentication scheme, called TouchWB, with 21 features that can be extracted from web browsing gestures. For evaluation, we implemented the scheme on Android phones and conducted a user study involving 48 participants. Experimental results demonstrated that our approach could reduce the touch behavioral deviation by nearly half and achieve an average error rate of about 2.4% by using a combined classifier of PSO-RBFN.
Original languageEnglish
JournalJournal of Network and Computer Applications
Volume117
Pages (from-to)1-9
Number of pages9
ISSN1084-8045
DOIs
Publication statusPublished - 2018

Keywords

  • Behavioral Authentication
  • Touch Gesture
  • Smartphone Security
  • Access Control
  • Touchscreen
  • Machine Learning

Cite this

Meng, Weizhi ; Wang, Yu ; Wong, Duncan S. ; Wen, Sheng ; Xiang, Yang. / TouchWB : Touch behavioral user authentication based on web browsing on smartphones. In: Journal of Network and Computer Applications. 2018 ; Vol. 117. pp. 1-9.
@article{2eed13cf40314abe9ea32b7895a2579e,
title = "TouchWB : Touch behavioral user authentication based on web browsing on smartphones",
abstract = "Modern mobile devices especially smartphones have rapidly evolved and are widely adopted by people of different ages. Smartphones can assist users in a variety of activities, i.e., from social networking to online shopping, but also have become an attractive target for cyber-criminals due to the stored personal data and sensitive information. The traditional authentication mechanisms like PIN suffer from well-known limitations and drawbacks in the security community; thus, touch behavioral authentication has recently received much attention. Intuitively, authentication based on free touches would be hard to build a stand-alone system. In this work, we advocate that such authentication can consider users’ actions under certain phone applications like web browser, and then propose a touch gesture-based authentication scheme, called TouchWB, with 21 features that can be extracted from web browsing gestures. For evaluation, we implemented the scheme on Android phones and conducted a user study involving 48 participants. Experimental results demonstrated that our approach could reduce the touch behavioral deviation by nearly half and achieve an average error rate of about 2.4{\%} by using a combined classifier of PSO-RBFN.",
keywords = "Behavioral Authentication, Touch Gesture, Smartphone Security, Access Control, Touchscreen, Machine Learning",
author = "Weizhi Meng and Yu Wang and Wong, {Duncan S.} and Sheng Wen and Yang Xiang",
year = "2018",
doi = "10.1016/j.jnca.2018.05.010",
language = "English",
volume = "117",
pages = "1--9",
journal = "Journal of Network and Computer Applications",
issn = "1084-8045",
publisher = "Academic Press",

}

TouchWB : Touch behavioral user authentication based on web browsing on smartphones. / Meng, Weizhi; Wang, Yu; Wong, Duncan S.; Wen, Sheng; Xiang, Yang.

In: Journal of Network and Computer Applications, Vol. 117, 2018, p. 1-9.

Research output: Contribution to journalJournal articleResearchpeer-review

TY - JOUR

T1 - TouchWB : Touch behavioral user authentication based on web browsing on smartphones

AU - Meng, Weizhi

AU - Wang, Yu

AU - Wong, Duncan S.

AU - Wen, Sheng

AU - Xiang, Yang

PY - 2018

Y1 - 2018

N2 - Modern mobile devices especially smartphones have rapidly evolved and are widely adopted by people of different ages. Smartphones can assist users in a variety of activities, i.e., from social networking to online shopping, but also have become an attractive target for cyber-criminals due to the stored personal data and sensitive information. The traditional authentication mechanisms like PIN suffer from well-known limitations and drawbacks in the security community; thus, touch behavioral authentication has recently received much attention. Intuitively, authentication based on free touches would be hard to build a stand-alone system. In this work, we advocate that such authentication can consider users’ actions under certain phone applications like web browser, and then propose a touch gesture-based authentication scheme, called TouchWB, with 21 features that can be extracted from web browsing gestures. For evaluation, we implemented the scheme on Android phones and conducted a user study involving 48 participants. Experimental results demonstrated that our approach could reduce the touch behavioral deviation by nearly half and achieve an average error rate of about 2.4% by using a combined classifier of PSO-RBFN.

AB - Modern mobile devices especially smartphones have rapidly evolved and are widely adopted by people of different ages. Smartphones can assist users in a variety of activities, i.e., from social networking to online shopping, but also have become an attractive target for cyber-criminals due to the stored personal data and sensitive information. The traditional authentication mechanisms like PIN suffer from well-known limitations and drawbacks in the security community; thus, touch behavioral authentication has recently received much attention. Intuitively, authentication based on free touches would be hard to build a stand-alone system. In this work, we advocate that such authentication can consider users’ actions under certain phone applications like web browser, and then propose a touch gesture-based authentication scheme, called TouchWB, with 21 features that can be extracted from web browsing gestures. For evaluation, we implemented the scheme on Android phones and conducted a user study involving 48 participants. Experimental results demonstrated that our approach could reduce the touch behavioral deviation by nearly half and achieve an average error rate of about 2.4% by using a combined classifier of PSO-RBFN.

KW - Behavioral Authentication

KW - Touch Gesture

KW - Smartphone Security

KW - Access Control

KW - Touchscreen

KW - Machine Learning

U2 - 10.1016/j.jnca.2018.05.010

DO - 10.1016/j.jnca.2018.05.010

M3 - Journal article

VL - 117

SP - 1

EP - 9

JO - Journal of Network and Computer Applications

JF - Journal of Network and Computer Applications

SN - 1084-8045

ER -