Computer-Based Testing (CBT) has gained prominence in Nigeria due to its efficiency and scalability in evaluating students across various educational institutions. However, various forms of exam cheating, such as candidate swapping and unauthorised assistance, threaten its integrity. This research explores the application of Convolutional Neural Networks (CNNs) for identity verification in Nigerian CBT environments and presents a CNN-driven facial biometric model based on the findings. The model extracts facial features of examinees from real-time videos of CBT exam sessions, and it compares them with pre-registered data to verify test takers' identities, as well as to detect and report instances of candidate swapping and unauthorised assistance during the ongoing exam. The model is trained on diverse datasets like VGGFace2 and CASIA African Face Dataset to enhance fairness and accuracy for African demographics. This ensures effectiveness in Nigerian Computer-Based Testing (CBT) and local contexts. Evaluation of the model and its comparative analysis with existing systems and other biometric methods were performed. The assessment involved 2,000 genuine and 3000 impostor samples, achieving 99.52% accuracy with high precision and recall of 0.998 and 0.99, respectively. The results demonstrate the model’s high accuracy, low false acceptance, and minimal false rejection rates, and highlight the model’s viability in maintaining exam integrity and accessibility.