AUTOMATED DETECTION OF EXAM MALPRACTICE

Abstract: Exam malpractice significantly undermines the reliability of digital and remote examination systems. Traditional manual invigilation lacks scalability and accuracy, leading to inconsistencies in supervision. This project proposes an AI-driven solution integrating Real-time Monitoring, Object Detection, and Human Monitoring for automated malpractice detection. The system utilizes computer vision and deep learning algorithms to analyze live or recorded video streams, identifying anomalies such as multiple human presences, unauthorized devices, and irregular motion patterns. Through continuous behavioural tracking and object classification, the framework ensures high- precision detection of suspicious activities, thereby enhancing academic integrity, examination security, and operational efficiency in online and offline assessment environments.

Keywords: Real-time Monitoring, Object Detection, Human Monitoring, Academic integrity.