Date of Award
Authentication, Biometrics, Classification, Keystroke Dynamics, k-NN, SVM
Security of data in recent times has become paramount, which has led to the development of many security systems. Among such systems is keystroke dynamics. Keystroke dynamics has become an active area of research in recent times. This is due, in part, to the increased importance of cyber-security, computer or network access control. Also known as typing dynamics, keystroke refers to a method that identifies users/individuals based on the manner of their typing pattern or rhythm on the keyboard, which could either mean a user is verified (identified) or authenticated. User identification is a critical factor before authentication. Now with a person already identified, the next step is to authenticate. Even if the user types in a correct password, that does not mean that the user is whom they say they are. The focus of this thesis is on the dynamic approach of keystrokes. In this work, we propose a method with improves our classification algorithm. We introduce a method that uses the minimum redundancy maximum relevance feature selection method which selects the best features based on the relevance and redundancy. We have also used several classifiers that include vector machine, k-nearest neighbour, Naive Bayes and grid search for optimizing the support vector machine. The results not only show the efficiency of our method but also show that the proposed method can be applied to other datasets to produce optimal results.
Ogemuno, Emamuzo Cletus, "Behavioural Based Biometrics Using Keystroke Dynamics for User Authentication" (2018). Electronic Theses and Dissertations. 7423.