Unobtrusive multimodal biometrics for ensuring privacy and information security with personal devices

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

45 Citations (Scopus)

Abstract

The need for authenticating users of ubiquitous mobile devices is becoming ever more critical with the increasing value of information stored in the devices and of services accessed via them. Passwords and conventional biometrics such as fingerprint recognition offer fairly reliable solutions to this problem, but these methods require explicit user authentication and are used mainly when a mobile device is being switched on. Furthermore, conventional biometrics are sometimes perceived as privacy threats. This paper presents an unobtrusive method of user authentication for mobile devices in the form of recognition of the walking style (gait) and voice of the user while carrying and using the device. While speaker recognition in noisy conditions performs poorly, combined speaker and accelerometer-based gait recognition performs significantly better. In tentative tests with 31 users the Equal Error Rate varied between 2% and 12% depending on noise conditions, typically less than half of the Equal Error Rates of individual modalities.

Original languageEnglish
Title of host publicationPervasive Computing
Subtitle of host publication4th International Conference, PERVASIVE 2006, Proceedings
PublisherSpringer
Pages187-201
ISBN (Print)3-540-33894-2, 978-3-540-33894-9
DOIs
Publication statusPublished - 1 Jan 2006
MoE publication typeA4 Article in a conference publication
Event4th International Conference on Pervasive Computing, PERVASIVE 2006 - Dublin, Ireland
Duration: 7 May 200610 May 2006

Publication series

SeriesLecture Notes in Computer Science
Volume3968
ISSN0302-9743

Conference

Conference4th International Conference on Pervasive Computing, PERVASIVE 2006
CountryIreland
CityDublin
Period7/05/0610/05/06

Fingerprint

Information Security
Biometrics
Security of data
Mobile devices
Mobile Devices
Privacy
User Authentication
Authentication
Error Rate
Gait Recognition
Fingerprint Recognition
Value of Information
Speaker Recognition
Password
Accelerometer
Gait
Accelerometers
Modality

Keywords

  • biometrics
  • user authentication
  • mobile devices
  • PDAs
  • walking style
  • accelerometer-based gait recognition

Cite this

Vildjiounaite, E., Mäkelä, S. M., Lindholm, M., Riihimäki, R., Kyllönen, V., Mäntyjärvi, J., & Ailisto, H. (2006). Unobtrusive multimodal biometrics for ensuring privacy and information security with personal devices. In Pervasive Computing: 4th International Conference, PERVASIVE 2006, Proceedings (pp. 187-201). Springer. Lecture Notes in Computer Science, Vol.. 3968 https://doi.org/10.1007/11748625_12
Vildjiounaite, Elena ; Mäkelä, Satu Marja ; Lindholm, Mikko ; Riihimäki, Reima ; Kyllönen, Vesa ; Mäntyjärvi, Jani ; Ailisto, Heikki. / Unobtrusive multimodal biometrics for ensuring privacy and information security with personal devices. Pervasive Computing: 4th International Conference, PERVASIVE 2006, Proceedings. Springer, 2006. pp. 187-201 (Lecture Notes in Computer Science, Vol. 3968).
@inproceedings{3c147e60ecfa4cb0ad707a1d57b5c94c,
title = "Unobtrusive multimodal biometrics for ensuring privacy and information security with personal devices",
abstract = "The need for authenticating users of ubiquitous mobile devices is becoming ever more critical with the increasing value of information stored in the devices and of services accessed via them. Passwords and conventional biometrics such as fingerprint recognition offer fairly reliable solutions to this problem, but these methods require explicit user authentication and are used mainly when a mobile device is being switched on. Furthermore, conventional biometrics are sometimes perceived as privacy threats. This paper presents an unobtrusive method of user authentication for mobile devices in the form of recognition of the walking style (gait) and voice of the user while carrying and using the device. While speaker recognition in noisy conditions performs poorly, combined speaker and accelerometer-based gait recognition performs significantly better. In tentative tests with 31 users the Equal Error Rate varied between 2{\%} and 12{\%} depending on noise conditions, typically less than half of the Equal Error Rates of individual modalities.",
keywords = "biometrics, user authentication, mobile devices, PDAs, walking style, accelerometer-based gait recognition",
author = "Elena Vildjiounaite and M{\"a}kel{\"a}, {Satu Marja} and Mikko Lindholm and Reima Riihim{\"a}ki and Vesa Kyll{\"o}nen and Jani M{\"a}ntyj{\"a}rvi and Heikki Ailisto",
note = "CA2: TK706",
year = "2006",
month = "1",
day = "1",
doi = "10.1007/11748625_12",
language = "English",
isbn = "3-540-33894-2",
series = "Lecture Notes in Computer Science",
publisher = "Springer",
pages = "187--201",
booktitle = "Pervasive Computing",
address = "Germany",

}

Vildjiounaite, E, Mäkelä, SM, Lindholm, M, Riihimäki, R, Kyllönen, V, Mäntyjärvi, J & Ailisto, H 2006, Unobtrusive multimodal biometrics for ensuring privacy and information security with personal devices. in Pervasive Computing: 4th International Conference, PERVASIVE 2006, Proceedings. Springer, Lecture Notes in Computer Science, vol. 3968, pp. 187-201, 4th International Conference on Pervasive Computing, PERVASIVE 2006, Dublin, Ireland, 7/05/06. https://doi.org/10.1007/11748625_12

Unobtrusive multimodal biometrics for ensuring privacy and information security with personal devices. / Vildjiounaite, Elena; Mäkelä, Satu Marja; Lindholm, Mikko; Riihimäki, Reima; Kyllönen, Vesa; Mäntyjärvi, Jani; Ailisto, Heikki.

Pervasive Computing: 4th International Conference, PERVASIVE 2006, Proceedings. Springer, 2006. p. 187-201 (Lecture Notes in Computer Science, Vol. 3968).

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

TY - GEN

T1 - Unobtrusive multimodal biometrics for ensuring privacy and information security with personal devices

AU - Vildjiounaite, Elena

AU - Mäkelä, Satu Marja

AU - Lindholm, Mikko

AU - Riihimäki, Reima

AU - Kyllönen, Vesa

AU - Mäntyjärvi, Jani

AU - Ailisto, Heikki

N1 - CA2: TK706

PY - 2006/1/1

Y1 - 2006/1/1

N2 - The need for authenticating users of ubiquitous mobile devices is becoming ever more critical with the increasing value of information stored in the devices and of services accessed via them. Passwords and conventional biometrics such as fingerprint recognition offer fairly reliable solutions to this problem, but these methods require explicit user authentication and are used mainly when a mobile device is being switched on. Furthermore, conventional biometrics are sometimes perceived as privacy threats. This paper presents an unobtrusive method of user authentication for mobile devices in the form of recognition of the walking style (gait) and voice of the user while carrying and using the device. While speaker recognition in noisy conditions performs poorly, combined speaker and accelerometer-based gait recognition performs significantly better. In tentative tests with 31 users the Equal Error Rate varied between 2% and 12% depending on noise conditions, typically less than half of the Equal Error Rates of individual modalities.

AB - The need for authenticating users of ubiquitous mobile devices is becoming ever more critical with the increasing value of information stored in the devices and of services accessed via them. Passwords and conventional biometrics such as fingerprint recognition offer fairly reliable solutions to this problem, but these methods require explicit user authentication and are used mainly when a mobile device is being switched on. Furthermore, conventional biometrics are sometimes perceived as privacy threats. This paper presents an unobtrusive method of user authentication for mobile devices in the form of recognition of the walking style (gait) and voice of the user while carrying and using the device. While speaker recognition in noisy conditions performs poorly, combined speaker and accelerometer-based gait recognition performs significantly better. In tentative tests with 31 users the Equal Error Rate varied between 2% and 12% depending on noise conditions, typically less than half of the Equal Error Rates of individual modalities.

KW - biometrics

KW - user authentication

KW - mobile devices

KW - PDAs

KW - walking style

KW - accelerometer-based gait recognition

UR - http://www.scopus.com/inward/record.url?scp=33745899934&partnerID=8YFLogxK

U2 - 10.1007/11748625_12

DO - 10.1007/11748625_12

M3 - Conference article in proceedings

AN - SCOPUS:33745899934

SN - 3-540-33894-2

SN - 978-3-540-33894-9

T3 - Lecture Notes in Computer Science

SP - 187

EP - 201

BT - Pervasive Computing

PB - Springer

ER -

Vildjiounaite E, Mäkelä SM, Lindholm M, Riihimäki R, Kyllönen V, Mäntyjärvi J et al. Unobtrusive multimodal biometrics for ensuring privacy and information security with personal devices. In Pervasive Computing: 4th International Conference, PERVASIVE 2006, Proceedings. Springer. 2006. p. 187-201. (Lecture Notes in Computer Science, Vol. 3968). https://doi.org/10.1007/11748625_12