Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM64203
Volume:
10 |
5 |
May 2026
Pages:
1-6
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.
Department of Computer Science & Engineering
Miracle Educational Society Group of Institutions
Department of Computer Science & Engineering
Miracle Educational Society Group of Institutions
Department of Computer Science & Engineering
Miracle Educational Society Group of Institutions
Department of Computer Science & Engineering
Miracle Educational Society Group of Institutions
This paper discusses the design of an intelligent video proctoring system aimed at securing remote evaluations and interviews. This multi-faceted platform incorporates artificial intelligence, computer vision, and modern web technologies (to provide real-time continuous identity verification and monitoring for behavioral anomalies) in order to facilitate secure remote assessments. At the core of the system is a facial recognition algorithm (DeepFace) utilizing the ArcFace algorithm for face matching. MediaPipe is utilized to perform gaze tracking, head pose estimation, and facial landmark recognition. Anomalies are detected based upon browser level activity such as tab switching or screen interruption and are flagged for atypical behavior based upon these same events. An instant fraud alert is sent to the administrator via a WebSocket after evaluating all of the signals from the three location anomaly sources using a weighted assessment score. The application's architecture employs React, TypeScript, FastAPI and Python to enable low latency, distributed processes with scalable capabilities. User management with role-based access control (RBAC), JWT authentication, encrypted session communication, event-based audit logging, etc. enhance the remote assessment's integrity, limit impersonation, create transparency during on-line assessments and provide reliability in employment decisions.
KEYWORDS
Intelligent Video Proctoring System (IVPS) will offer a viable, expandable, and AI-based solution that provides secure monitoring of online tests and remote interviews; it will offer seamless integration between current online technologies and the application of artificial intelligence and computer vision to continually verify a person's identity, monitor one's behavior and provide real-time detection of fraud. A major component of facial recognition and tracking (marking eye movement) and head posture is via DeepFace/MediaPipe—this allows for accurate surveillance of all methods used by candidates to take the exam. The combination of analysis of browser activity and an overall fraud score for all of the fraud children of each participant provides further security and anomaly detection through improved reliability and reduced limitations compared to previously used online proctoring methods, when many methods of monitoring were combined together.The architecture of this development has shown evidence that real-time communications, alerting, and centralized logging via ;with WebRTC and WebSocket show effective performance. In terms of combining multiple monitoring and observational methods will greatly enhance the effectiveness of providing quality monitoring results..
1. R. D, H. C, E. S, H. A, and K. R.: Smart Proctor: Lightweight, Privacy-Centric Remote Exam Monitoring. International Journal For Multidisciplinary Research (2025) 2. J. R. Pansare: Proctoring Using AI. International Journal For Science Technology And Engineering 13(6) (2025) 1825–1835 3. S. S. Benazer, S. K. Ramamoorthy, and S. M. Kamali: An AI-Based Intelligent Exam Proctoring System for Secure and Fair Online Assessments. (2024) 4. A. Patil, P. A. Chavan, S. R. Jadhav, A. U. Phodkar, M. B. Gulame, and A. P. Pimpalkar: Online Exam Proctoring Application Using-AI. International Journal of Science and Research Archive 15(2) (2025) 1228–1234 5. P. Shrivastav, S. Mishra, S. S, and S. K. G: AI-Powered Multimodal Approach for Secure Online Examinations. (2025) 1520–1525 6. V. L. Priya, A. G. Naidu, I. M. Manikanta, C. S. Kumar, B. I. Preetham, and S. Muthumeena: Proctonix AI - Smart Exam Proctoring using AI and Webcam. (2025) 1762–1768 7. M. P and V. K: AI-Powered Real-Time Proctoring System for Secure Online Examinations. (2025) 8. S. A. Pascual: AI-Powered Online Exam Proctoring System for Secure and Scalable Assessment. Indian Scientific Journal Of Research In Engineering And Management 09(06) (2025) 1–9 9. S. S. Benazer, S. K. Ramamoorthy, and S. M. Kamali: An AI-Based Intelligent Exam Proctoring System for Secure and Fair Online Assessments. (2024) 10. V. R, P. P. Rao, M. S. N, and N. A: Virtual Overseer for Examination Using Artificial Intelligence. Indonesian Journal of Information Systems (2024)
Publication Date
5/28/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
0
Total views since publication
PDF Downloads
3
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...