A Robust e-Invigilation System Employing Multimodal Biometric Authentication

Abstract

Abstract-The significant growth in users of e-learning technologies and their use in courses has given rise to a major concern over protecting them from misuse; a significant concern is that of the potential for cheating or illicit assistance during online examinations. This paper presents the development of robust, flexible, transparent and continuous authentication mechanism for e-assessments. To monitor the exam taker and ensure that only the legitimate student is taking the exam, the system offers a continuous user identification employing multimodal biometrics; a security layer using an eye tracker to record the student's eye movement; and, speech recognition to detect inappropriate communication. The focus of this paper in particular is the development and evaluation of 3D facial authentication. An experiment has been conducted to investigate the ability of the proposed platform to detect any cheating attempts. During the experiment, participants' biometric data, eye movement, and head movements have been collected using custom software. The 3D camera also captured the session using a built-in microphone and the system recognized speech (employing a speech recognition algorithm). 51 participants participated in this experiment. The FRR of all legitimate participants was 0 and 0.0063 in 2D and 3D facial recognition modes respectively. Furthermore, three participants were tasked with a series of eight scenarios that map to typical misuse. The results of the FAR and FRR of five of these threat scenarios in both 2D and 3D mode were 0 with two cases exhibiting an FAR of 0.11 and 0.076 in the 2D mode.

A Systematic Survey on Examinees Identity Authentication in Online Distant Exams

“…Jackn, Kevin developed an initial method for a continuous authentication system using Face, voice, and fingerprint as individual biometric modes for simulating channels with different temporal characteristics [156]. Ketab, Clarke and Dowland proposed a novel e-invigilation system design incorporated a range of behavioral and physiological biometrics, including face recognition, keystroke analysis, mouse dynamics, linguistic analysis, and iris recognition for continuous student identification in differing examination scenarios (e.g., essay writing, multiple-choice test) [157]. Liu, Jiang and Devenere proposed two models for secure e-examinations propose; the Interactive and Secure e-Examination Unit (ISEEU) is the first model, and it has two ways.…”

Continuous and Transparent E-Invigilation of E-Assessments

“…The principle of ease of use has been given a high priority in this part of the system; the system provides many simple windows with clear instructions. All the student need is to do is to enter their domain username and password, and the system will recognize them and lead them to an appropriate page that enables them to: Biometric enrolment or re-enrolment, security calibration, review available tests, schedule available tests, and take available tests [34]. Once the enrolment process is completed, the student can login to the test, and the system will direct them to an automated and controlled invigilation environment as shown in Figure 10.…”

“…Therefore, care will still need to be taken in poorly illuminated rooms or environments where the camera is positioned, where the quality or angle of the capture may prove problematic. However, the nature of the eye tracking is to ensure that the eyes are in the view of the screen, which is exactly where the face recognition camera needs them to be in order to get both eyes; thus, the orientation is essentially fixed automatically as a product of the design of the system [34]. Additionally, the system basically needs appropriate illumination in order to allow the user to access the test, so these should help ensure providing the required level of illumination during the rest of the test.…”

User Authentication by Eye Movement Features Employing SVM and XGBoost Classifiers

“…The device will not work if it does not detect the user's moving eyeballs. Even the use of a mask is problematic in such a situation, as it may slightly obscure the eyes, which will cause the eye tracker to work incorrectly [8].…”