Canada Spends Logo

Explorez notre analyse du budget 2026

Grant: Discovery Grants Program - Individual

University of Victoria

$36,000.00

Intelligent framework for efficient and effective risk-based authentication

EF 2013-14

Résumé
In today's globally expanding business world, protecting the identity and transactions of online consumers is crucial for any company to reach out for new market. This directs digital information technologies towards theadoption of stronger and more secure authentication schemes. Traditional password scheme is notoriously flawed. Alternatives or complements to password scheme are hardware-based authentication devices, whose widespread adoption has been hindered by their high costs and complexities as well as customers reluctance to use such devices. Therefore, the development of cost-effective and low-impact mechanisms that strengthen online authentication without the need for hardware-based authentication devices becomes an imperative.Risk-based authentication is an emerging approach for online authentication that fits this category of authentication technologies. Risk-based authentication consists of extracting and analyzing both contextual and historical user information, as well as data generated during Internet communications, to assess the probability a user interaction is authentic. Unfortunately, despite their high convenience and low cost, existing risk-based authentication technologies are plagued by their relatively high false positives and false negatives rates. This is rooted in the fact that existing risk-based authentication models are built on rule engines that use a combination of parameters such as IP address and location to create patterns to compare with those in future authorization attempts.Rule-based (RB) techniques, however, are operationally ineffective due to the rapidly evolving nature of online fraud patterns and the strong variability characterizing human behavior. Such cases cannot be completely covered by static rules from a rule base system. The purpose of this research is to investigate new risk-based authentication approach and mechanims that exhibit automatic pattern recognition and self-learning capabilities, in order to effectively and efficiently find new patterns to prevent fraud.
Programme
Discovery Grants Program - Individual
Emplacement
British Columbia, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data

Tel que publié

Application id
227556-2009
Name nom
Traore, Issa
Department département
Electrical and Computer Engineering
Organization id
7
Institution établissement
University of Victoria
Province en
British Columbia
Province fr
Colombie-Britannique
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2013
Competition year année de concours
2009
Award amount
36000
Program id
RGPIN
Program name en
Discovery Grants Program - Individual
Program name fr
Programme de subventions à la découverte - individuelles
Group en
Discovery grants programs
Group fr
Programmes de subventions à la découverte
Committee code
1079
Committee name en
Electrical and Computer Engineering
Committee name fr
Génie électrique et de l'informatique
Area of application code
801
Area of application group en
Information and communication services
Area of application group fr
Services d'information et de télécommunications
Area of application en
Computer software
Area of application fr
Logiciel
Research subject code
2710
Research subject group en
Information technology
Research subject group fr
Technologie de l'information
Research subject en
Information systems design
Research subject fr
Conception de systèmes d'information
Partie
5
Nb partie
6
Application title
Intelligent framework for efficient and effective risk-based authentication
Keyword
NSERC
Application summary
In today's globally expanding business world, protecting the identity and transactions of online consumers is crucial for any company to reach out for new market. This directs digital information technologies towards theadoption of stronger and more secure authentication schemes. Traditional password scheme is notoriously flawed. Alternatives or complements to password scheme are hardware-based authentication devices, whose widespread adoption has been hindered by their high costs and complexities as well as customers reluctance to use such devices. Therefore, the development of cost-effective and low-impact mechanisms that strengthen online authentication without the need for hardware-based authentication devices becomes an imperative.Risk-based authentication is an emerging approach for online authentication that fits this category of authentication technologies. Risk-based authentication consists of extracting and analyzing both contextual and historical user information, as well as data generated during Internet communications, to assess the probability a user interaction is authentic. Unfortunately, despite their high convenience and low cost, existing risk-based authentication technologies are plagued by their relatively high false positives and false negatives rates. This is rooted in the fact that existing risk-based authentication models are built on rule engines that use a combination of parameters such as IP address and location to create patterns to compare with those in future authorization attempts.Rule-based (RB) techniques, however, are operationally ineffective due to the rapidly evolving nature of online fraud patterns and the strong variability characterizing human behavior. Such cases cannot be completely covered by static rules from a rule base system. The purpose of this research is to investigate new risk-based authentication approach and mechanims that exhibit automatic pattern recognition and self-learning capabilities, in order to effectively and efficiently find new patterns to prevent fraud.