An Efficient Optimized Mouse and Keystroke Dynamics Framework for Continuous Non-Intrusive User Authentication

Online learning has entirely transformed the way of learning by the students. Online tests and quizzes play an important role in online learning, which provides accurate results to the instructor. But, the learners use different methods to cheat during online exams such as opening a browser to search for the answer or a document in the local drive, etc. They are not authenticated once they login and progress to attend the online exams. Different techniques are used in authenticating the students taking up the online exams such as audio or video surveillance systems, fingerprint, or iris recognition, etc. Keystroke dynamics-based authentication (KDA) method, a behavioral biometric-based authentication model has gained focus in authenticating the users. This chapter proposes the usage of KDA as a solution to user authentication in online exams and presents a detailed review on the processes of KDA, the factors that affect the performance of KDA, their applications in different domains, and a few keystroke dynamics-based datasets to authenticate the users during online exams.

Download Full-text

Continuous User Authentication Based on Keystroke Dynamics through Neural Network Committee Machines

Continuous Authentication Using Biometrics ◽

10.4018/978-1-61350-129-0.ch011 ◽

2011 ◽

pp. 232-252

Author(s):

Sérgio Roberto de Lima e Silva Filho ◽

Mauro Roisenberg

Keyword(s):

Neural Network ◽

Neural Networks ◽

User Authentication ◽

Keystroke Dynamics ◽

Continuous Authentication ◽

Biometric Characteristic ◽

Continuous User ◽

Computer Keyboard

This chapter proposes an authentication methodology that is both inexpensive and non-intrusive and authenticates users continuously while using a computer keyboard. This proposed methodology uses neural network committee machines. The committee consists of several independent neural networks trained to recognize a behavioral biometric characteristic: user’s typing pattern. Continuous authentication prevents potential attacks when users leave their desks without logging out or locking their computer session. Some experiments were conducted to evaluate and to calibrate the authentication committee. Best results show that a 0% FAR and a 0.15% FRR can be achieved when different thresholds are used in the system for each user. In this proposed methodology, capture system does not need to concern about typing errors in the text. Another feature of this methodology is that new users can be easily added to the system, with no need to re-train all neural networks involved.

Download Full-text