Exploring How User Routine Affects the Recognition Performance of a Lock Pattern

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

19 Downloads (Pure)

Abstract

To protect an Android smartphone against attackers, a lock pattern can be used. Nevertheless, shoulder-surfing and smudge attacks can be used to get access despite of this protection. To combat these attacks, biometric recognition can be added to the lock pattern, such that the lock-pattern application keeps track of the way users draw the pattern. This research explores how users change the way they draw lock patterns over time and its effect on the recognition performance of the pattern. A lock-pattern dataset has been collected and a classifier is proposed. In this research the best result was obtained using the x- and y-coordinate as the user's biometrics. Unfortunately, in this paper it is shown that adding biometrics to a lock pattern is only an additional security that provides no guarantee for a secure lock pattern. It is just a small improvement over using a lock pattern without biometric identification.
Original languageUndefined
Title of host publicationProceedings of the 2015 International Conference of the Biometrics Special Interest Group (BIOSIG)
Place of PublicationBonn
PublisherGesellschaft für Informatik
Pages1-8
Number of pages8
ISBN (Print)978-3-88579-639-8
DOIs
Publication statusPublished - 9 Sep 2015
Event14th International Conference of the Biometrics Special Interest Group 2015 - Darmstadt, Germany
Duration: 9 Sep 201511 Sep 2015
Conference number: 14

Publication series

NameLecture Notes in Informatics (LNI) - Proceedings
PublisherGesellschaft für Informatik
VolumeP-245
ISSN (Print)1617-5468

Conference

Conference14th International Conference of the Biometrics Special Interest Group 2015
Abbreviated titleBIOSIG 2015
CountryGermany
CityDarmstadt
Period9/09/1511/09/15

Keywords

  • EWI-26415
  • SCS-Safety
  • Smartphone
  • METIS-315003
  • IR-98076
  • Biometrics
  • lock pattern

Cite this

de Wide, L., Spreeuwers, L. J., & Veldhuis, R. N. J. (2015). Exploring How User Routine Affects the Recognition Performance of a Lock Pattern. In Proceedings of the 2015 International Conference of the Biometrics Special Interest Group (BIOSIG) (pp. 1-8). (Lecture Notes in Informatics (LNI) - Proceedings; Vol. P-245). Bonn: Gesellschaft für Informatik. https://doi.org/10.1109/BIOSIG.2015.7314603
de Wide, Lisa ; Spreeuwers, Lieuwe Jan ; Veldhuis, Raymond N.J. / Exploring How User Routine Affects the Recognition Performance of a Lock Pattern. Proceedings of the 2015 International Conference of the Biometrics Special Interest Group (BIOSIG). Bonn : Gesellschaft für Informatik, 2015. pp. 1-8 (Lecture Notes in Informatics (LNI) - Proceedings).
@inproceedings{5b3a97ddb9e74939b2c2d40ab64a3043,
title = "Exploring How User Routine Affects the Recognition Performance of a Lock Pattern",
abstract = "To protect an Android smartphone against attackers, a lock pattern can be used. Nevertheless, shoulder-surfing and smudge attacks can be used to get access despite of this protection. To combat these attacks, biometric recognition can be added to the lock pattern, such that the lock-pattern application keeps track of the way users draw the pattern. This research explores how users change the way they draw lock patterns over time and its effect on the recognition performance of the pattern. A lock-pattern dataset has been collected and a classifier is proposed. In this research the best result was obtained using the x- and y-coordinate as the user's biometrics. Unfortunately, in this paper it is shown that adding biometrics to a lock pattern is only an additional security that provides no guarantee for a secure lock pattern. It is just a small improvement over using a lock pattern without biometric identification.",
keywords = "EWI-26415, SCS-Safety, Smartphone, METIS-315003, IR-98076, Biometrics, lock pattern",
author = "{de Wide}, Lisa and Spreeuwers, {Lieuwe Jan} and Veldhuis, {Raymond N.J.}",
note = "10.1109/BIOSIG.2015.7314603",
year = "2015",
month = "9",
day = "9",
doi = "10.1109/BIOSIG.2015.7314603",
language = "Undefined",
isbn = "978-3-88579-639-8",
series = "Lecture Notes in Informatics (LNI) - Proceedings",
publisher = "Gesellschaft f{\"u}r Informatik",
pages = "1--8",
booktitle = "Proceedings of the 2015 International Conference of the Biometrics Special Interest Group (BIOSIG)",
address = "Germany",

}

de Wide, L, Spreeuwers, LJ & Veldhuis, RNJ 2015, Exploring How User Routine Affects the Recognition Performance of a Lock Pattern. in Proceedings of the 2015 International Conference of the Biometrics Special Interest Group (BIOSIG). Lecture Notes in Informatics (LNI) - Proceedings, vol. P-245, Gesellschaft für Informatik, Bonn, pp. 1-8, 14th International Conference of the Biometrics Special Interest Group 2015, Darmstadt, Germany, 9/09/15. https://doi.org/10.1109/BIOSIG.2015.7314603

Exploring How User Routine Affects the Recognition Performance of a Lock Pattern. / de Wide, Lisa; Spreeuwers, Lieuwe Jan; Veldhuis, Raymond N.J.

Proceedings of the 2015 International Conference of the Biometrics Special Interest Group (BIOSIG). Bonn : Gesellschaft für Informatik, 2015. p. 1-8 (Lecture Notes in Informatics (LNI) - Proceedings; Vol. P-245).

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

TY - GEN

T1 - Exploring How User Routine Affects the Recognition Performance of a Lock Pattern

AU - de Wide, Lisa

AU - Spreeuwers, Lieuwe Jan

AU - Veldhuis, Raymond N.J.

N1 - 10.1109/BIOSIG.2015.7314603

PY - 2015/9/9

Y1 - 2015/9/9

N2 - To protect an Android smartphone against attackers, a lock pattern can be used. Nevertheless, shoulder-surfing and smudge attacks can be used to get access despite of this protection. To combat these attacks, biometric recognition can be added to the lock pattern, such that the lock-pattern application keeps track of the way users draw the pattern. This research explores how users change the way they draw lock patterns over time and its effect on the recognition performance of the pattern. A lock-pattern dataset has been collected and a classifier is proposed. In this research the best result was obtained using the x- and y-coordinate as the user's biometrics. Unfortunately, in this paper it is shown that adding biometrics to a lock pattern is only an additional security that provides no guarantee for a secure lock pattern. It is just a small improvement over using a lock pattern without biometric identification.

AB - To protect an Android smartphone against attackers, a lock pattern can be used. Nevertheless, shoulder-surfing and smudge attacks can be used to get access despite of this protection. To combat these attacks, biometric recognition can be added to the lock pattern, such that the lock-pattern application keeps track of the way users draw the pattern. This research explores how users change the way they draw lock patterns over time and its effect on the recognition performance of the pattern. A lock-pattern dataset has been collected and a classifier is proposed. In this research the best result was obtained using the x- and y-coordinate as the user's biometrics. Unfortunately, in this paper it is shown that adding biometrics to a lock pattern is only an additional security that provides no guarantee for a secure lock pattern. It is just a small improvement over using a lock pattern without biometric identification.

KW - EWI-26415

KW - SCS-Safety

KW - Smartphone

KW - METIS-315003

KW - IR-98076

KW - Biometrics

KW - lock pattern

U2 - 10.1109/BIOSIG.2015.7314603

DO - 10.1109/BIOSIG.2015.7314603

M3 - Conference contribution

SN - 978-3-88579-639-8

T3 - Lecture Notes in Informatics (LNI) - Proceedings

SP - 1

EP - 8

BT - Proceedings of the 2015 International Conference of the Biometrics Special Interest Group (BIOSIG)

PB - Gesellschaft für Informatik

CY - Bonn

ER -

de Wide L, Spreeuwers LJ, Veldhuis RNJ. Exploring How User Routine Affects the Recognition Performance of a Lock Pattern. In Proceedings of the 2015 International Conference of the Biometrics Special Interest Group (BIOSIG). Bonn: Gesellschaft für Informatik. 2015. p. 1-8. (Lecture Notes in Informatics (LNI) - Proceedings). https://doi.org/10.1109/BIOSIG.2015.7314603