Comparison between Mixed Binary classification and Voting Technique for Active User Authentication using Mouse Dynamics

Alnour Ahmed Khalifa; Mutasim Adil Hassan; Tarig Ahmed Khalid; Hassan Hamdoun

doi:10.1109/ICCNEEE.2015.7381378

Comparison between Mixed Binary classification and Voting Technique for Active User Authentication using Mouse Dynamics

Alnour Ahmed Khalifa^*, Mutasim Adil Hassan, Tarig Ahmed Khalid, Hassan Hamdoun

^*Corresponding author for this work

University of Khartoum

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

5 Citations (Scopus)

7 Downloads (Pure)

Abstract

The rapid proliferation of computing processing power has facilitated a rise in the adoption of computers in various aspects of human lives. From education to shopping and other everyday activities to critical applications in finance, banking and, recently, degree awarding online education. Several approaches for user authentication based on Behavioral Biometrics (BB) were suggested in order to identify unique signature/footprint for improved matching accuracy for genuine users and flagging for abnormal behaviors from intruders. In this paper we present a comparison between two classification algorithms for identifying users' behavior using mouse dynamics. The algorithms are based on support vector machines (SVM) classifier allowing for direct comparison between different authentication-based metrics. The voting technique shows low False Acceptance Rate(FAR) and noticeably small learning time; making it more suitable for incorporation within different authentication applications.

Original language	English
Title of host publication	2015 International Conference on Computing, Control, Networking, Electronics and Embedded Systems Engineering (ICCNEEE)
Editors	RA Saeed, RA Mokhtar
Publisher	IEEE Press
Pages	281-286
Number of pages	6
ISBN (Electronic)	978-1-4673-7869-7
ISBN (Print)	978-1-4673-7870-3
DOIs	https://doi.org/10.1109/ICCNEEE.2015.7381378
Publication status	Published - 2015
Event	IEEEE- The International Conference on Computing, Control, Networking, Electronics and Embedded Systems Engineering (ICCNEEE 2015) - Sudan, Khartoum, Sudan Duration: 7 Sept 2015 → 9 Sept 2015

Conference

Conference	IEEEE- The International Conference on Computing, Control, Networking, Electronics and Embedded Systems Engineering (ICCNEEE 2015)
Country/Territory	Sudan
City	Khartoum
Period	7/09/15 → 9/09/15

Keywords

active authentication
mouse dynamics
pattern recognition
machine learning
support vector machines
Biometrics (access control)
Artificial neural networks

Access to Document

10.1109/ICCNEEE.2015.7381378Licence: Unspecified

ICCNEEE15-Mouse-Dynamics-finalv5_5Submitted manuscript, 359 KBLicence: Unspecified

Cite this

Khalifa, A. A., Hassan, M. A., Khalid, T. A., & Hamdoun, H. (2015). Comparison between Mixed Binary classification and Voting Technique for Active User Authentication using Mouse Dynamics. In RA. Saeed, & RA. Mokhtar (Eds.), 2015 International Conference on Computing, Control, Networking, Electronics and Embedded Systems Engineering (ICCNEEE) (pp. 281-286). IEEE Press. https://doi.org/10.1109/ICCNEEE.2015.7381378

Comparison between Mixed Binary classification and Voting Technique for Active User Authentication using Mouse Dynamics. / Khalifa, Alnour Ahmed; Hassan, Mutasim Adil; Khalid, Tarig Ahmed et al.
2015 International Conference on Computing, Control, Networking, Electronics and Embedded Systems Engineering (ICCNEEE). ed. / RA Saeed; RA Mokhtar. IEEE Press, 2015. p. 281-286.

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

Khalifa, AA, Hassan, MA, Khalid, TA & Hamdoun, H 2015, Comparison between Mixed Binary classification and Voting Technique for Active User Authentication using Mouse Dynamics. in RA Saeed & RA Mokhtar (eds), 2015 International Conference on Computing, Control, Networking, Electronics and Embedded Systems Engineering (ICCNEEE). IEEE Press, pp. 281-286, IEEEE- The International Conference on Computing, Control, Networking, Electronics and Embedded Systems Engineering (ICCNEEE 2015) , Khartoum, Sudan, 7/09/15. https://doi.org/10.1109/ICCNEEE.2015.7381378

Khalifa AA, Hassan MA, Khalid TA, Hamdoun H. Comparison between Mixed Binary classification and Voting Technique for Active User Authentication using Mouse Dynamics. In Saeed RA, Mokhtar RA, editors, 2015 International Conference on Computing, Control, Networking, Electronics and Embedded Systems Engineering (ICCNEEE). IEEE Press. 2015. p. 281-286 doi: 10.1109/ICCNEEE.2015.7381378

Khalifa, Alnour Ahmed ; Hassan, Mutasim Adil ; Khalid, Tarig Ahmed et al. / Comparison between Mixed Binary classification and Voting Technique for Active User Authentication using Mouse Dynamics. 2015 International Conference on Computing, Control, Networking, Electronics and Embedded Systems Engineering (ICCNEEE). editor / RA Saeed ; RA Mokhtar. IEEE Press, 2015. pp. 281-286

@inproceedings{e9e56ccf45784fc7829fc659d167848f,

title = "Comparison between Mixed Binary classification and Voting Technique for Active User Authentication using Mouse Dynamics",

abstract = "The rapid proliferation of computing processing power has facilitated a rise in the adoption of computers in various aspects of human lives. From education to shopping and other everyday activities to critical applications in finance, banking and, recently, degree awarding online education. Several approaches for user authentication based on Behavioral Biometrics (BB) were suggested in order to identify unique signature/footprint for improved matching accuracy for genuine users and flagging for abnormal behaviors from intruders. In this paper we present a comparison between two classification algorithms for identifying users' behavior using mouse dynamics. The algorithms are based on support vector machines (SVM) classifier allowing for direct comparison between different authentication-based metrics. The voting technique shows low False Acceptance Rate(FAR) and noticeably small learning time; making it more suitable for incorporation within different authentication applications.",

keywords = "active authentication, mouse dynamics, pattern recognition, machine learning, support vector machines, Biometrics (access control), Artificial neural networks",

author = "Khalifa, {Alnour Ahmed} and Hassan, {Mutasim Adil} and Khalid, {Tarig Ahmed} and Hassan Hamdoun",

year = "2015",

doi = "10.1109/ICCNEEE.2015.7381378",

language = "English",

isbn = "978-1-4673-7870-3",

pages = "281--286",

editor = "RA Saeed and RA Mokhtar",

booktitle = "2015 International Conference on Computing, Control, Networking, Electronics and Embedded Systems Engineering (ICCNEEE)",

publisher = "IEEE Press",

note = "IEEEE- The International Conference on Computing, Control, Networking, Electronics and Embedded Systems Engineering (ICCNEEE 2015) ; Conference date: 07-09-2015 Through 09-09-2015",

}

TY - GEN

T1 - Comparison between Mixed Binary classification and Voting Technique for Active User Authentication using Mouse Dynamics

AU - Khalifa, Alnour Ahmed

AU - Hassan, Mutasim Adil

AU - Khalid, Tarig Ahmed

AU - Hamdoun, Hassan

PY - 2015

Y1 - 2015

N2 - The rapid proliferation of computing processing power has facilitated a rise in the adoption of computers in various aspects of human lives. From education to shopping and other everyday activities to critical applications in finance, banking and, recently, degree awarding online education. Several approaches for user authentication based on Behavioral Biometrics (BB) were suggested in order to identify unique signature/footprint for improved matching accuracy for genuine users and flagging for abnormal behaviors from intruders. In this paper we present a comparison between two classification algorithms for identifying users' behavior using mouse dynamics. The algorithms are based on support vector machines (SVM) classifier allowing for direct comparison between different authentication-based metrics. The voting technique shows low False Acceptance Rate(FAR) and noticeably small learning time; making it more suitable for incorporation within different authentication applications.

AB - The rapid proliferation of computing processing power has facilitated a rise in the adoption of computers in various aspects of human lives. From education to shopping and other everyday activities to critical applications in finance, banking and, recently, degree awarding online education. Several approaches for user authentication based on Behavioral Biometrics (BB) were suggested in order to identify unique signature/footprint for improved matching accuracy for genuine users and flagging for abnormal behaviors from intruders. In this paper we present a comparison between two classification algorithms for identifying users' behavior using mouse dynamics. The algorithms are based on support vector machines (SVM) classifier allowing for direct comparison between different authentication-based metrics. The voting technique shows low False Acceptance Rate(FAR) and noticeably small learning time; making it more suitable for incorporation within different authentication applications.

KW - active authentication

KW - mouse dynamics

KW - pattern recognition

KW - machine learning

KW - support vector machines

KW - Biometrics (access control)

KW - Artificial neural networks

U2 - 10.1109/ICCNEEE.2015.7381378

DO - 10.1109/ICCNEEE.2015.7381378

M3 - Published conference contribution

SN - 978-1-4673-7870-3

SP - 281

EP - 286

BT - 2015 International Conference on Computing, Control, Networking, Electronics and Embedded Systems Engineering (ICCNEEE)

A2 - Saeed, RA

A2 - Mokhtar, RA

PB - IEEE Press

T2 - IEEEE- The International Conference on Computing, Control, Networking, Electronics and Embedded Systems Engineering (ICCNEEE 2015)

Y2 - 7 September 2015 through 9 September 2015

ER -

Comparison between Mixed Binary classification and Voting Technique for Active User Authentication using Mouse Dynamics

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this