Intelligent Candidate Monitoring and Interview Surveillance System for Virtual Interview

Abstract

The Secure Interview Monitoring System is a web-based interviewing tool that helps keep track of the test environment with the assistance of a web camera as a real test proctor. It works in the background and identifies suspicious actions like head movements, use of mobile phones, and even the presence of other persons and issues alerts on the spot to ensure integrity. Every activity is documented to be reviewed. Automated analysis recognizes possible red flags and transforms an ordinary video call into a safe and monitored space, which is defined as an intelligent system. It is created in a way that guarantees equity and dependability of remote employment without the need to have a human monitoring it all the time.

Introduction

Existing remote proctoring tools rely on basic video recording, motion detection, or advanced AI techniques like face tracking and gaze detection. However, these systems often suffer from major issues such as high false alarms, privacy concerns, heavy computational requirements, and inability to accurately distinguish between normal behavior (like looking away briefly) and actual cheating. Some systems are too simplistic and miss cheating, while others are overly strict and intrusive, creating distrust and anxiety among candidates.

Advanced approaches using computer vision (e.g., gaze tracking, object detection, behavioral pattern analysis) improve accuracy but still face limitations in privacy, fairness, and real-time effectiveness. A major gap in existing systems is the lack of balanced, context-aware monitoring that can detect real cheating without over-flagging normal behavior.

To address these issues, the proposed SIMS system acts as a real-time, locally operating “silent proctor.” It uses the webcam to monitor candidate behavior, detect suspicious actions (such as looking at a phone, using notes, or another person entering the room), and provides immediate on-screen alerts while also recording events. Unlike traditional systems, it focuses on real-time intervention instead of post-exam review.

Conclusion

That nagging doubt during a remote interview? It’s there for a reason. Is this actually fair? Could someone slip something by? For the longest time, the answer was pretty unsatisfying. But keeping things honest doesn’t have to mean watching every blink or listening to every breath. Sometimes, it’s just about paying smart attention. So, that’s what this system does. It simply notices where someone’s looking and what’s in the room, then speaks up right away if something’s not right. No complicated setups, no delays. It just works.

References

[1] A. S. Rathore and T. N. Goh, \"AI-based Proctoring Systems: A Survey of Methods, Challenges and Ethics,\" IEEE Access, vol. 10, pp. 34521–34542, 2022. [2] L. Martinez, J. Rodriguez, and R. Chen, \"Real-Time Head Pose Estimation Using MediaPipe for Online Exam Monitoring\", Proc. Int. Conf. on Computer Vision and Pattern Recognition Workshops, 2021, pp. 410–418. [3] K. Sharma and P. Verma, \"YOLO-Based Object Detection for Unauthorized Item Recognition in Remote Assessments,\" Journal of Artificial Intelligence in Education, vol. 32, no. 3, pp. 521–540, 2021. [4] M. Lee and S. Park, \"Fairness and Privacy in Automated Exam Proctoring: A Student- Centric Analysis,\" Computers & Education, vol. 178, 104301, 2022. [5] B. R. Smith, T. O\'Neil, and J. A. Kim, \"Behavioral Integrity Monitoring in Remote Testing Using Computer Vision and Gaze Tracking,\" Int. Journal of Distance Education Technologies, vol. 20, no. 2, pp. 33–52, 2022. [6] R. J. Wilson et al., \"Screen Recording and Video Audit Trails in Online Proctoring: Legal and Ethical Implications,\" Journal of Cybersecurity and Privacy, vol. 3, no. 1, pp. 78–95, 2023. [7] N. Gupta and A. Desai, \"False Positives in AI Proctoring: Causes, Impact, and Mitigation,\" Proc. ACM Conf. on Learning @ Scale, 2022, pp. 215–224. [8] C. Torres and E. Fernandez, \"Local-Only Proctoring: A Privacy-Preserving Approach to Remote Exam Integrity,\" IEEE Security & Privacy Workshops, 2023, pp. 122–130. [9] S. Zhao and H. Li, \"Multimodal Cheating Detection in Online Exams Using Facial Landmarks and Object Recognition,\" Proc. Int. Conf. on Educational Data Mining, 2021, pp. 320–329. [10] P. Zhang and L. Wang, \"Real-Time Alert Systems for Academic Integrity: Design and Usability Study,\" Behaviour & Information Technology, vol. 41, no. 9, pp. 1889–1905, 2022.

Copyright

Copyright © 2026 Dr. T. Manoj Prasath, V. Sakthi Varshini , D. Dhana Lakshmi , N. Sumuthuradevi . This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.