Open Access

ARTICLE

Deep Learning Models for Detecting Cheating in Online Exams

Siham Essahraui¹, Ismail Lamaakal¹, Yassine Maleh^2,*, Khalid El Makkaoui¹, Mouncef Filali Bouami¹, Ibrahim Ouahbi¹, May Almousa³, Ali Abdullah S. AlQahtani⁴, Ahmed A. Abd El-Latif^5,6

1 Multidisciplinary Faculty of Nador, Mohammed Premier University, Oujda, 60000, Morocco
2 Laboratory LaSTI, ENSAK, Sultan Moulay Slimane University, Khouribga, 54000, Morocco
3 Department of Information Technology, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman University, P.O. Box 84428, Riyadh, 11671, Saudi Arabia
4 College of Computer and Information Sciences, Prince Sultan University, Riyadh, 11586, Saudi Arabia
5 EIAS Data Science Lab, College of Computer and Information Sciences, and Center of Excellence in Quantum and Intelligent Computing, Prince Sultan University, Riyadh, 11586, Saudi Arabia
6 Department of Mathematics and Computer Science, Faculty of Science, Menoufia University, Shebin El-Koom, 32511, Egypt

* Corresponding Author: Yassine Maleh. Email:

Computers, Materials & Continua 2025, 85(2), 3151-3183. https://doi.org/10.32604/cmc.2025.067359

Received 01 May 2025; Accepted 16 June 2025; Issue published 23 September 2025

Abstract

The rapid shift to online education has introduced significant challenges to maintaining academic integrity in remote assessments, as traditional proctoring methods fall short in preventing cheating. The increase in cheating during online exams highlights the need for efficient, adaptable detection models to uphold academic credibility. This paper presents a comprehensive analysis of various deep learning models for cheating detection in online proctoring systems, evaluating their accuracy, efficiency, and adaptability. We benchmark several advanced architectures, including EfficientNet, MobileNetV2, ResNet variants and more, using two specialized datasets (OEP and OP) tailored for online proctoring contexts. Our findings reveal that EfficientNetB1 and YOLOv5 achieve top performance on the OP dataset, with EfficientNetB1 attaining a peak accuracy of 94.59% and YOLOv5 reaching a mean average precision (mAP@0.5) of 98.3%. For the OEP dataset, ResNet50-CBAM, YOLOv5 and EfficientNetB0 stand out, with ResNet50-CBAM achieving an accuracy of 93.61% and EfficientNetB0 showing robust detection performance with balanced accuracy and computational efficiency. These results underscore the importance of selecting models that balance accuracy and efficiency, supporting scalable, effective cheating detection in online assessments.

---

Keywords

---