Thursday, June 11, 2020 - 13:00 to 14:30
SCHOOL OF COMPUTER SCIENCE
The School of Computer Science is pleased to present…
MSc Thesis Defense by: Anjali Shah
Date: Thursday, June 11th, 2020
Time: 1:00 pm to 2:30 pm
ZOOM Meeting URL: https://zoom.us/j/92609468725?
Authentication systems are the first line of defence against passive access attacks. Nowadays, modern authentication systems require advanced authentication technology. It becomes uncommon for any authentication system to rely on password-based authentication as the primary means for verifying user identity. The adaptation of other authentication technologies is snowballing across many sectors. One such promising authentication technology is biometrics. Biometrics authentication technologies verify the user's identity using unique physical or behavioural characteristics of the user. In recent years the behavioural biometrics technologies have risen in popularity because of their appealing features and the rise of machine learning and artificial intelligence (AI). In fact, market studies show that the global behavioural biometrics market size was valued at $720.50 million in 2017, and the behavioural biometrics market forecast is projected to reach $3,922.42 million by 2025. However, engineering practical behavioural-based biometric systems for user verification and authentication is a complex process.
In this thesis, we argue that most of the work in the literature on behavioural-based biometric systems using AI and machine learning is immature and unreliable. Our analysis and experimental results show that designing reliable behavioural-based biometric systems requires a systematic and complicated process. We first discuss the limitation in existing work and the use of conventional machine learning methods. We use the Biometric Zoos theory to demonstrate the challenge of designing reliable behavioural-based biometric systems. Then, we outline the common problems in engineering reliable biometric system. In particular, we focus on the need for novelty detection machine learning models and adaptive machine learning algorithms. We provide a systematic approach to design and build reliable behavioural-based biometric systems. In our study, we apply the proposed approach to keystroke dynamics. Keystroke dynamics is behavioural-based biometric that identify individuals by measuring their unique typing behaviours on physical or soft keyboards. Our study shows that it is possible to design reliable behavioural-based biometric and addresses the gaps that exist in the literature.
Keywords: Authentication Systems, Biometrics, Keystroke Biometrics, Novelty Detection, Adaptive Machine Learning
Internal Reader: Dr. Boubakeur Boufama
External Reader: Dr. Ahmed Azab
Advisor: Dr. Sherif Saad Ahmed
Chair: Dr. Alhadidi
MSc Thesis Defense Announcement
5113 Lambton Tower 401 Sunset Ave. Windsor ON, N9B 3P4 (519) 253-3000 Ext. 3716 firstname.lastname@example.org