An HMM-based behavior modeling approach for continuous mobile authentication

Aditi Roy, Tzipora Halevi, Nasir Memon

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper studies continuous authentication for touch interface based mobile devices. A Hidden Markov Model (HMM) based behavioral template training approach is presented, which does not require training data from other subjects other than the owner of the mobile. The stroke patterns of a user are modeled using a continuous left-right HMM. The approach models the horizontal and vertical scrolling patterns of a user since these are the basic and mostly used interactions on a mobile device. The effectiveness of the proposed method is evaluated through extensive experiments using the Toucha-lytics database which comprises of touch data over time. The results show that the performance of the proposed approach is better than the state-of-the-art method.

Original languageEnglish (US)
Title of host publication2014 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2014
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages3789-3793
Number of pages5
ISBN (Print)9781479928927
DOIs
StatePublished - 2014
Event2014 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2014 - Florence, Italy
Duration: May 4 2014May 9 2014

Other

Other2014 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2014
CountryItaly
CityFlorence
Period5/4/145/9/14

Fingerprint

Hidden Markov models
Mobile devices
Authentication
Experiments

Keywords

  • Behavioral biometric
  • Continuous authentication
  • Hidden Markov Model
  • Security
  • Touch pattern

ASJC Scopus subject areas

  • Signal Processing
  • Software
  • Electrical and Electronic Engineering

Cite this

Roy, A., Halevi, T., & Memon, N. (2014). An HMM-based behavior modeling approach for continuous mobile authentication. In 2014 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2014 (pp. 3789-3793). [6854310] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICASSP.2014.6854310

An HMM-based behavior modeling approach for continuous mobile authentication. / Roy, Aditi; Halevi, Tzipora; Memon, Nasir.

2014 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2014. Institute of Electrical and Electronics Engineers Inc., 2014. p. 3789-3793 6854310.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Roy, A, Halevi, T & Memon, N 2014, An HMM-based behavior modeling approach for continuous mobile authentication. in 2014 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2014., 6854310, Institute of Electrical and Electronics Engineers Inc., pp. 3789-3793, 2014 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2014, Florence, Italy, 5/4/14. https://doi.org/10.1109/ICASSP.2014.6854310
Roy A, Halevi T, Memon N. An HMM-based behavior modeling approach for continuous mobile authentication. In 2014 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2014. Institute of Electrical and Electronics Engineers Inc. 2014. p. 3789-3793. 6854310 https://doi.org/10.1109/ICASSP.2014.6854310
Roy, Aditi ; Halevi, Tzipora ; Memon, Nasir. / An HMM-based behavior modeling approach for continuous mobile authentication. 2014 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2014. Institute of Electrical and Electronics Engineers Inc., 2014. pp. 3789-3793
@inproceedings{fe50d5de12a5487f86467632f3e9b1dd,
title = "An HMM-based behavior modeling approach for continuous mobile authentication",
abstract = "This paper studies continuous authentication for touch interface based mobile devices. A Hidden Markov Model (HMM) based behavioral template training approach is presented, which does not require training data from other subjects other than the owner of the mobile. The stroke patterns of a user are modeled using a continuous left-right HMM. The approach models the horizontal and vertical scrolling patterns of a user since these are the basic and mostly used interactions on a mobile device. The effectiveness of the proposed method is evaluated through extensive experiments using the Toucha-lytics database which comprises of touch data over time. The results show that the performance of the proposed approach is better than the state-of-the-art method.",
keywords = "Behavioral biometric, Continuous authentication, Hidden Markov Model, Security, Touch pattern",
author = "Aditi Roy and Tzipora Halevi and Nasir Memon",
year = "2014",
doi = "10.1109/ICASSP.2014.6854310",
language = "English (US)",
isbn = "9781479928927",
pages = "3789--3793",
booktitle = "2014 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2014",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - An HMM-based behavior modeling approach for continuous mobile authentication

AU - Roy, Aditi

AU - Halevi, Tzipora

AU - Memon, Nasir

PY - 2014

Y1 - 2014

N2 - This paper studies continuous authentication for touch interface based mobile devices. A Hidden Markov Model (HMM) based behavioral template training approach is presented, which does not require training data from other subjects other than the owner of the mobile. The stroke patterns of a user are modeled using a continuous left-right HMM. The approach models the horizontal and vertical scrolling patterns of a user since these are the basic and mostly used interactions on a mobile device. The effectiveness of the proposed method is evaluated through extensive experiments using the Toucha-lytics database which comprises of touch data over time. The results show that the performance of the proposed approach is better than the state-of-the-art method.

AB - This paper studies continuous authentication for touch interface based mobile devices. A Hidden Markov Model (HMM) based behavioral template training approach is presented, which does not require training data from other subjects other than the owner of the mobile. The stroke patterns of a user are modeled using a continuous left-right HMM. The approach models the horizontal and vertical scrolling patterns of a user since these are the basic and mostly used interactions on a mobile device. The effectiveness of the proposed method is evaluated through extensive experiments using the Toucha-lytics database which comprises of touch data over time. The results show that the performance of the proposed approach is better than the state-of-the-art method.

KW - Behavioral biometric

KW - Continuous authentication

KW - Hidden Markov Model

KW - Security

KW - Touch pattern

UR - http://www.scopus.com/inward/record.url?scp=84905276953&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84905276953&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2014.6854310

DO - 10.1109/ICASSP.2014.6854310

M3 - Conference contribution

AN - SCOPUS:84905276953

SN - 9781479928927

SP - 3789

EP - 3793

BT - 2014 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2014

PB - Institute of Electrical and Electronics Engineers Inc.

ER -