Competition between SOM clusters to model user authentication system in computer networks

Shrijit S. Joshi; Vir V. Phoha

doi:10.1109/COMSWA.2007.382421

Competition between SOM clusters to model user authentication system in computer networks

Shrijit S. Joshi, Vir V. Phoha

Research output: Chapter in Book/Entry/Poem › Conference contribution

7 Scopus citations

Abstract

Traditional authentication systems employed on Internet are facing an acute problem of intrusions. In this context we propose a neural architecture for user authentication through keystroke dynamics. Proposed architecture consists of a set of self organizing maps where each user has a distinct map. Each map consists of n neurons in the input layer where n is the length of a keystroke pattern; however to determine the number of neurons in the output layer, a strategy is proposed. For authenticating claimed user, probable user(s) for a given pattern and the degree of similarity between the map of the claimed user and a given pattern are determined. Finally, a decision on the authenticity is made using threshold criteria. Evaluation results show the best false accept rate of 0.88% when false reject rate was 3.55% with authentication accuracy of 97.83%. An application scenario of the method in a computer network environment is also presented.

Original language	English (US)
Title of host publication	Proceedings of the 2007 2nd International Conference on Communication System Software and Middleware and Workshops, COMSWARE 2007
DOIs	https://doi.org/10.1109/COMSWA.2007.382421
State	Published - Oct 1 2007
Externally published	Yes
Event	2007 2nd International Conference on Communication System Software and Middleware and Workshops, COMSWARE 2007 - Bangalore, India Duration: Jan 7 2007 → Jan 12 2007

Publication series

Name	Proceedings of the 2007 2nd International Conference on Communication System Software and Middleware and Workshops, COMSWARE 2007

Other

Other	2007 2nd International Conference on Communication System Software and Middleware and Workshops, COMSWARE 2007
Country/Territory	India
City	Bangalore
Period	1/7/07 → 1/12/07

Keywords

Computer security
Keystroke dynamics
Self organizing map
User authentication

ASJC Scopus subject areas

Computer Networks and Communications
Software
Electrical and Electronic Engineering

Access to Document

10.1109/COMSWA.2007.382421

Cite this

Joshi, S. S., & Phoha, V. V. (2007). Competition between SOM clusters to model user authentication system in computer networks. In Proceedings of the 2007 2nd International Conference on Communication System Software and Middleware and Workshops, COMSWARE 2007 [4268064] (Proceedings of the 2007 2nd International Conference on Communication System Software and Middleware and Workshops, COMSWARE 2007). https://doi.org/10.1109/COMSWA.2007.382421

Competition between SOM clusters to model user authentication system in computer networks. / Joshi, Shrijit S.; Phoha, Vir V.
Proceedings of the 2007 2nd International Conference on Communication System Software and Middleware and Workshops, COMSWARE 2007. 2007. 4268064 (Proceedings of the 2007 2nd International Conference on Communication System Software and Middleware and Workshops, COMSWARE 2007).

Research output: Chapter in Book/Entry/Poem › Conference contribution

Joshi, SS & Phoha, VV 2007, Competition between SOM clusters to model user authentication system in computer networks. in Proceedings of the 2007 2nd International Conference on Communication System Software and Middleware and Workshops, COMSWARE 2007., 4268064, Proceedings of the 2007 2nd International Conference on Communication System Software and Middleware and Workshops, COMSWARE 2007, 2007 2nd International Conference on Communication System Software and Middleware and Workshops, COMSWARE 2007, Bangalore, India, 1/7/07. https://doi.org/10.1109/COMSWA.2007.382421

Joshi SS, Phoha VV. Competition between SOM clusters to model user authentication system in computer networks. In Proceedings of the 2007 2nd International Conference on Communication System Software and Middleware and Workshops, COMSWARE 2007. 2007. 4268064. (Proceedings of the 2007 2nd International Conference on Communication System Software and Middleware and Workshops, COMSWARE 2007). doi: 10.1109/COMSWA.2007.382421

Joshi, Shrijit S. ; Phoha, Vir V. / Competition between SOM clusters to model user authentication system in computer networks. Proceedings of the 2007 2nd International Conference on Communication System Software and Middleware and Workshops, COMSWARE 2007. 2007. (Proceedings of the 2007 2nd International Conference on Communication System Software and Middleware and Workshops, COMSWARE 2007).

@inproceedings{aea1038d68294830bb91e5c2028508b6,

title = "Competition between SOM clusters to model user authentication system in computer networks",

abstract = "Traditional authentication systems employed on Internet are facing an acute problem of intrusions. In this context we propose a neural architecture for user authentication through keystroke dynamics. Proposed architecture consists of a set of self organizing maps where each user has a distinct map. Each map consists of n neurons in the input layer where n is the length of a keystroke pattern; however to determine the number of neurons in the output layer, a strategy is proposed. For authenticating claimed user, probable user(s) for a given pattern and the degree of similarity between the map of the claimed user and a given pattern are determined. Finally, a decision on the authenticity is made using threshold criteria. Evaluation results show the best false accept rate of 0.88% when false reject rate was 3.55% with authentication accuracy of 97.83%. An application scenario of the method in a computer network environment is also presented.",

keywords = "Computer security, Keystroke dynamics, Self organizing map, User authentication",

author = "Joshi, {Shrijit S.} and Phoha, {Vir V.}",

year = "2007",

month = oct,

day = "1",

doi = "10.1109/COMSWA.2007.382421",

language = "English (US)",

isbn = "1424406145",

series = "Proceedings of the 2007 2nd International Conference on Communication System Software and Middleware and Workshops, COMSWARE 2007",

booktitle = "Proceedings of the 2007 2nd International Conference on Communication System Software and Middleware and Workshops, COMSWARE 2007",

note = "2007 2nd International Conference on Communication System Software and Middleware and Workshops, COMSWARE 2007 ; Conference date: 07-01-2007 Through 12-01-2007",

}

TY - GEN

T1 - Competition between SOM clusters to model user authentication system in computer networks

AU - Joshi, Shrijit S.

AU - Phoha, Vir V.

PY - 2007/10/1

Y1 - 2007/10/1

N2 - Traditional authentication systems employed on Internet are facing an acute problem of intrusions. In this context we propose a neural architecture for user authentication through keystroke dynamics. Proposed architecture consists of a set of self organizing maps where each user has a distinct map. Each map consists of n neurons in the input layer where n is the length of a keystroke pattern; however to determine the number of neurons in the output layer, a strategy is proposed. For authenticating claimed user, probable user(s) for a given pattern and the degree of similarity between the map of the claimed user and a given pattern are determined. Finally, a decision on the authenticity is made using threshold criteria. Evaluation results show the best false accept rate of 0.88% when false reject rate was 3.55% with authentication accuracy of 97.83%. An application scenario of the method in a computer network environment is also presented.

AB - Traditional authentication systems employed on Internet are facing an acute problem of intrusions. In this context we propose a neural architecture for user authentication through keystroke dynamics. Proposed architecture consists of a set of self organizing maps where each user has a distinct map. Each map consists of n neurons in the input layer where n is the length of a keystroke pattern; however to determine the number of neurons in the output layer, a strategy is proposed. For authenticating claimed user, probable user(s) for a given pattern and the degree of similarity between the map of the claimed user and a given pattern are determined. Finally, a decision on the authenticity is made using threshold criteria. Evaluation results show the best false accept rate of 0.88% when false reject rate was 3.55% with authentication accuracy of 97.83%. An application scenario of the method in a computer network environment is also presented.

KW - Computer security

KW - Keystroke dynamics

KW - Self organizing map

KW - User authentication

UR - http://www.scopus.com/inward/record.url?scp=34748884294&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34748884294&partnerID=8YFLogxK

U2 - 10.1109/COMSWA.2007.382421

DO - 10.1109/COMSWA.2007.382421

M3 - Conference contribution

AN - SCOPUS:34748884294

SN - 1424406145

SN - 9781424406142

T3 - Proceedings of the 2007 2nd International Conference on Communication System Software and Middleware and Workshops, COMSWARE 2007

BT - Proceedings of the 2007 2nd International Conference on Communication System Software and Middleware and Workshops, COMSWARE 2007

T2 - 2007 2nd International Conference on Communication System Software and Middleware and Workshops, COMSWARE 2007

Y2 - 7 January 2007 through 12 January 2007

ER -

Competition between SOM clusters to model user authentication system in computer networks

Abstract

Publication series

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this