INTEGRATING MACHINE LEARNING AND STATISTICAL METHODS FOR SECURE INTRANET-BASED COMPUTER-BASED TESTING ENVIRONMENTS

Abstract

Computer-Based Testing (CBT) systems have become increasingly prevalent in educational and professional settings, offering advantages in efficiency and scalability. However, these systems are vulnerable to a range of security threats, including unauthorized access, data breaches, and cheating. Traditional security measures, while effective to some extent, are often insufficient to address the dynamic and sophisticated nature of these threats. This paper presents a novel framework that integrates machine learning and statistical methods to enhance the security and integrity of intranet-based CBT environments. The proposed framework leverages machine learning algorithms for real-time anomaly detection and threat prediction, coupled with statistical models for continuous monitoring and risk assessment. The integration of these techniques enables the system to identify and respond to security breaches more effectively than conventional approaches. A case study is presented, demonstrating the application of the framework in a real-world CBT system. The results show significant improvements in detecting and mitigating security threats, thereby ensuring the reliability of the testing process. Key performance indicators, including detection accuracy and response time, are analyzed to evaluate the framework’s effectiveness. The findings highlight the potential of combining machine learning with statistical methods to create a robust and adaptive security solution for CBT systems. This research contributes to the ongoing efforts to secure digital assessment environments, providing a foundation for future advancements in the field.