Hidden Monitoring Based on Keystroke Dynamics in Online Examination System

Abstract

The COVID-19 pandemic has accelerated the development of distance learning technologies, where online tests and exams play an important role. In online testing, the detection of various types of academic fraud, including cases where the examinee is falsely represented by another person, is of particular importance. Continuous biometric (behavioral) authentication can be a solution to counter unauthorized access. This paper proposes an authentication technology based on keystroke dynamics and hidden monitoring. An application for collecting and updating keystroke dynamics profiles of domain users and their continuous authentication is developed. The efficiency of reducing the dimension of the keystroke feature space based on the frequency of alphabetic letters is demonstrated. Results of popular performance metrics (FAR, FRR, ERR, ROC, and DET) are significantly improved already when evaluating only metric distances. For instance, ERR is reduced from 10.1% to 0.79%, which is comparable to the estimates provided by the kNN method for its optimal parameters.

A Deep-Learning-Based Approach to Keystroke-Injection Payload Generation

“…The evaluation of accuracy and performance in free-text keystroke dynamics is an ongoing area of investigation; researchers are actively developing methods to minimize error rates in this domain [46], while other researchers have explored the application of cGAN networks to generate fake keystroke dynamics patterns with the intention of deceiving keystroke-authentication systems [47]. Given the growing need for remote learning, continuous authentication with keystroke dynamics was implemented and performed very effectively [48], although keystroke dynamics has significant inaccuracies when applied to RDP (remote desktop protocol) and VNC (virtual network computing) systems, resulting in poor or non-functioning operation.…”