Homogeneous cognitive based biometrics for static authentication
| dc.contributor.author | Mohamed, Omar Hamdy | |
| dc.contributor.supervisor | Traoré, Issa | |
| dc.date.accessioned | 2011-02-01T23:06:52Z | |
| dc.date.available | 2011-02-01T23:06:52Z | |
| dc.date.copyright | 2010 | en |
| dc.date.issued | 2011-02-01T23:06:52Z | |
| dc.degree.department | Department of Electrical and Computer Engineering | |
| dc.degree.level | Doctor of Philosophy Ph.D. | en |
| dc.description.abstract | 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 markets. This directs digital information technologies towards the adoption of stronger and more secure authentication schemes. Increasingly, such biometric-based user authentication systems have proven superiority over the traditional ones (such as username/password). Unfortunately, despite the significant advances accomplished in developing biometric technologies, there are several barriers to their wide-scale deployment and application for Internet security. Additionally, introducing new biometrics faces similar barriers and challenges such as expensive equipment, or low-precision sensor technologies. In this research, we propose a novel biometric system for static user authentication, that homogeneously combines mouse dynamics, visual search capability and short-term memory effect. The proposed system introduces the visual search capability, and short-term memory effect to the biometric-based security world for the first time. The use of mouse for its dynamics, and as an input sensor for the other two biometrics, means no additional hardware is required. Experimental evaluation demonstrated the system's effectiveness using variable or one-time passwords. All of these attributes qualify the proposed system to be effectively deployed as a static Web-authentication mechanism. Extensive experimentation was done using 2740 sessions collected from 274 users. Two classification mechanisms were used to measure the performance. Using the first of these, a specially devised neural network model called Divide & Select, an EER of 5.7% was achieved. A computational statistics model showed a higher classification performance; a statistical classifier design called Weighted-Sum produced an EER of 2.1%. The performance enhancement produced as a result of changing the analysis model suggests that with further analysis, performance could be enhanced to an industry standard level. Additionally, we presented a Proof of Concept (POC) system to show the system packaging practicality. | en |
| dc.identifier.uri | http://hdl.handle.net/1828/3211 | |
| dc.language | English | eng |
| dc.language.iso | en | en |
| dc.rights | Available to the World Wide Web | en |
| dc.subject | authentication schemes | en |
| dc.subject | biometric technologies | en |
| dc.subject | internet security | en |
| dc.subject.lcsh | UVic Subject Index::Sciences and Engineering::Applied Sciences::Computer science | en |
| dc.title | Homogeneous cognitive based biometrics for static authentication | en |
| dc.type | Thesis | en |