Mobile based continuous authentication using deep features

Mario Parreño Centeno; Yu Guan; Aad van Moorsel

doi:10.1145/3212725.3212732

Mobile based continuous authentication using deep features

Mario Parreño Centeno
, Yu Guan
, Aad van Moorsel

Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Continuous authentication is a promising approach to validate the user’s identity during a work session, e.g., for mobile banking applications. Recently, it has been demonstrated that changes in the motion patterns of the user may help to note the unauthorised use of mobile devices. Several approaches have been proposed in this area but with relatively weak performance results. In this work, we propose an approach which uses a Siamese convolutional neural network to learn the signatures of the motion patterns from users and achieve a competitive verification accuracy up to 97.8%. We also find our algorithm is not very sensitive to sampling frequency and the length of the sequence.

Original language	English
Title of host publication	EMDL 2018 - Proceedings of the 2018 International Workshop on Embedded and Mobile Deep Learning
Publisher	Association for Computing Machinery
Pages	19-24
Number of pages	6
ISBN (Electronic)	9781450358446
DOIs	https://doi.org/10.1145/3212725.3212732
Publication status	Published - 15 Jun 2018
Event	2nd International Workshop on Embedded and Mobile Deep Learning, EMDL 2018 - Munich, Germany Duration: 15 Jun 2018 → 15 Jun 2018

Publication series

Name	EMDL 2018 - Proceedings of the 2018 International Workshop on Embedded and Mobile Deep Learning

Conference

Conference	2nd International Workshop on Embedded and Mobile Deep Learning, EMDL 2018
Country/Territory	Germany
City	Munich
Period	15/06/18 → 15/06/18

Bibliographical note

Publisher Copyright:
© 2018 Association for Computing Machinery.

Keywords

Biometrics
Continuous authentication
Learning latent representations
Motion authentication
Siamese CNN

ASJC Scopus subject areas

Information Systems
Software
Hardware and Architecture
Computer Science Applications

Access to Document

10.1145/3212725.3212732

Cite this

Centeno, M. P., Guan, Y., & van Moorsel, A. (2018). Mobile based continuous authentication using deep features. In EMDL 2018 - Proceedings of the 2018 International Workshop on Embedded and Mobile Deep Learning (pp. 19-24). (EMDL 2018 - Proceedings of the 2018 International Workshop on Embedded and Mobile Deep Learning). Association for Computing Machinery. https://doi.org/10.1145/3212725.3212732

@inproceedings{586723466d9144069b2b2f20513065db,

title = "Mobile based continuous authentication using deep features",

abstract = "Continuous authentication is a promising approach to validate the user{\textquoteright}s identity during a work session, e.g., for mobile banking applications. Recently, it has been demonstrated that changes in the motion patterns of the user may help to note the unauthorised use of mobile devices. Several approaches have been proposed in this area but with relatively weak performance results. In this work, we propose an approach which uses a Siamese convolutional neural network to learn the signatures of the motion patterns from users and achieve a competitive verification accuracy up to 97.8\%. We also find our algorithm is not very sensitive to sampling frequency and the length of the sequence.",

keywords = "Biometrics, Continuous authentication, Learning latent representations, Motion authentication, Siamese CNN",

author = "Centeno, \{Mario Parre{\~n}o\} and Yu Guan and \{van Moorsel\}, Aad",

note = "Publisher Copyright: {\textcopyright} 2018 Association for Computing Machinery.; 2nd International Workshop on Embedded and Mobile Deep Learning, EMDL 2018 ; Conference date: 15-06-2018 Through 15-06-2018",

year = "2018",

month = jun,

day = "15",

doi = "10.1145/3212725.3212732",

language = "English",

series = "EMDL 2018 - Proceedings of the 2018 International Workshop on Embedded and Mobile Deep Learning",

publisher = "Association for Computing Machinery",

pages = "19--24",

booktitle = "EMDL 2018 - Proceedings of the 2018 International Workshop on Embedded and Mobile Deep Learning",

}

Centeno, MP, Guan, Y & van Moorsel, A 2018, Mobile based continuous authentication using deep features. in EMDL 2018 - Proceedings of the 2018 International Workshop on Embedded and Mobile Deep Learning. EMDL 2018 - Proceedings of the 2018 International Workshop on Embedded and Mobile Deep Learning, Association for Computing Machinery, pp. 19-24, 2nd International Workshop on Embedded and Mobile Deep Learning, EMDL 2018, Munich, Germany, 15/06/18. https://doi.org/10.1145/3212725.3212732

Mobile based continuous authentication using deep features. / Centeno, Mario Parreño; Guan, Yu; van Moorsel, Aad.
EMDL 2018 - Proceedings of the 2018 International Workshop on Embedded and Mobile Deep Learning. Association for Computing Machinery, 2018. p. 19-24 (EMDL 2018 - Proceedings of the 2018 International Workshop on Embedded and Mobile Deep Learning).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Mobile based continuous authentication using deep features

AU - Centeno, Mario Parreño

AU - Guan, Yu

AU - van Moorsel, Aad

PY - 2018/6/15

Y1 - 2018/6/15

N2 - Continuous authentication is a promising approach to validate the user’s identity during a work session, e.g., for mobile banking applications. Recently, it has been demonstrated that changes in the motion patterns of the user may help to note the unauthorised use of mobile devices. Several approaches have been proposed in this area but with relatively weak performance results. In this work, we propose an approach which uses a Siamese convolutional neural network to learn the signatures of the motion patterns from users and achieve a competitive verification accuracy up to 97.8%. We also find our algorithm is not very sensitive to sampling frequency and the length of the sequence.

AB - Continuous authentication is a promising approach to validate the user’s identity during a work session, e.g., for mobile banking applications. Recently, it has been demonstrated that changes in the motion patterns of the user may help to note the unauthorised use of mobile devices. Several approaches have been proposed in this area but with relatively weak performance results. In this work, we propose an approach which uses a Siamese convolutional neural network to learn the signatures of the motion patterns from users and achieve a competitive verification accuracy up to 97.8%. We also find our algorithm is not very sensitive to sampling frequency and the length of the sequence.

KW - Biometrics

KW - Continuous authentication

KW - Learning latent representations

KW - Motion authentication

KW - Siamese CNN

UR - https://www.scopus.com/pages/publications/85058235000

U2 - 10.1145/3212725.3212732

DO - 10.1145/3212725.3212732

M3 - Conference contribution

AN - SCOPUS:85058235000

T3 - EMDL 2018 - Proceedings of the 2018 International Workshop on Embedded and Mobile Deep Learning

SP - 19

EP - 24

BT - EMDL 2018 - Proceedings of the 2018 International Workshop on Embedded and Mobile Deep Learning

PB - Association for Computing Machinery

T2 - 2nd International Workshop on Embedded and Mobile Deep Learning, EMDL 2018

Y2 - 15 June 2018 through 15 June 2018

ER -

Centeno MP, Guan Y, van Moorsel A. Mobile based continuous authentication using deep features. In EMDL 2018 - Proceedings of the 2018 International Workshop on Embedded and Mobile Deep Learning. Association for Computing Machinery. 2018. p. 19-24. (EMDL 2018 - Proceedings of the 2018 International Workshop on Embedded and Mobile Deep Learning). doi: 10.1145/3212725.3212732

Mobile based continuous authentication using deep features

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this