Comparative Evaluation of ResNet-50, MobileNetV2, and EfficientNet for Real-Time Exam Cheating Detection and Chatbot-Based Alert System

Nanang Prihatin; Herri Mahyar; Muhammad Azzahari; Muhammad Kahfi Aulia

doi:10.52436/1.jutif.2026.7.4.5687

Authors

Nanang Prihatin Department of Information and Computer Technology, Politeknik Negeri Lhokseumawe, Indonesia
Herri Mahyar Department of Civil Engineering, Politeknik Negeri Lhokseumawe, Indonesia
Muhammad Azzahari Department of Information and Computer Technology, Politeknik Negeri Lhokseumawe, Indonesia
Muhammad Kahfi Aulia Medical Informatics Study Program, Universitas Bumi Persada, Indonesia

DOI:

https://doi.org/10.52436/1.jutif.2026.7.4.5687

Keywords:

Academic Integrity, Convolutional Neural Network, Exam Cheating Detection, Real-Time Monitoring

Abstract

Academic integrity during examinations remains a persistent challenge, as conventional human-based supervision often struggles to detect subtle cheating behaviors. This study proposes the development of a camera-based exam cheating detection system leveraging transfer learning with state-of-the-art Convolutional Neural Network (CNN) architectures. Three pretrained models—ResNet-50, MobileNetV2, and EfficientNet—were comparatively evaluated to identify suspicious gestures such as peeking at peers or using hidden notes. The first training phase utilized a publicly available dataset from Kaggle, where ResNet-50 outperformed the other models, achieving a validation accuracy of 98.7% with an F1-score of 0.987. To further assess robustness, a second training phase was conducted using a newly collected private dataset reflecting real exam scenarios. With only 10 epochs, ResNet-50 maintained strong generalization performance, reaching a test accuracy of 97.7%. These results highlight the consistency of ResNet-50 across different datasets and conditions. The selected model was subsequently integrated into a prototype application capable of real-time monitoring and instant notifications via chatbot, enabling timely intervention by exam supervisors. The findings underscore the critical role of model selection in real-time AI proctoring systems and provide a benchmarked, scalable solution that advances the field of computer vision-based academic integrity monitoring.

Downloads

Download data is not yet available.

References

P. Anitha and S. Sundaram, “Prevalence, Types and Reasons for Academic Dishonesty among College Students,” J. Stud. Soc. Sci. Humanit., vol. 7, no. 1, pp. 1–14, 2021.

O. L. Holden, M. E. Norris, and V. A. Kuhlmeier, “Academic Integrity in Online Assessment: A Research Review,” Front. Educ., vol. 6, no. July, pp. 1–13, 2021, doi: 10.3389/feduc.2021.639814.

S. Arab and S. N. Orfan, “Perceptions of Afghan EFL undergraduate students about exam cheating,” Cogent Arts Humanit., vol. 10, no. 1, Dec. 2023, doi: 10.1080/23311983.2023.2215564.

T. M. Fritz, H. G. Cruz, S. C. Rudert, S. Janke, and M. Daumiller, “Goals, norms, attitudes, and self-efficacy as predictors of academic dishonesty: Two-wave prospective inquiries into additive and multiplicative effects,” Ethics Behav., pp. 1–20, Feb. 2026, doi: 10.1080/10508422.2026.2622321.

T.-C. Phan, A.-C. Phan, and H.-D. Tran, “Exam Cheating Detection Based on Action Recognition Using Vision Transformer,” in Intelligent Systems and Data Science, Oct. 2024, pp. 65–77. doi: 10.1007/978-981-99-7649-2_6.

L. Benson and R. Enstroem, “A model for preventing academic misconduct: evidence from a large-scale intervention,” Int. J. Educ. Integr., vol. 19, no. 1, pp. 1–17, 2023, doi: 10.1007/s40979-023-00147-y.

J. K. Forbes, “The relationship between higher education faculty’s motivation to report suspected academic dishonesty and likelihood to report,” Int. J. Educ. Integr., vol. 21, no. 1, 2025, doi: 10.1007/s40979-025-00200-y.

G. Kadayam Guruswami, S. Mumtaz, A. Gopakumar, E. Khan, F. Abdullah, and S. K. Parahoo, “Academic Integrity Perceptions Among Health-Professions’ Students: A Cross-Sectional Study in The Middle East,” J. Acad. Ethics, vol. 21, no. 2, pp. 231–249, 2023, doi: 10.1007/s10805-022-09452-6.

P. J. Miles, M. Campbell, and G. D. Ruxton, “Why Students Cheat and How Understanding This Can Help Reduce the Frequency of Academic Misconduct in Higher Education: A Literature Review,” J. Undergrad. Neurosci. Educ., vol. 20, no. 2, pp. a150–a160, 2022, doi: 10.59390/lxmj2920.

M. Sozon, O. H. Mohammad Alkharabsheh, P. W. Fong, and S. B. Chuan, “Cheating and plagiarism in higher education institutions (HEIs): A literature review,” F1000Research, vol. 13, no. May, pp. 1–34, 2024, doi: 10.12688/f1000research.147140.2.

A. Sarwat, K. Vaidehi, and M. Sowmya, “Human Activity Recognition Using CNN and LSTM Methods,” J. Basic Sci., vol. 22, no. 11, pp. 367–381, 2022, doi: 10.37896/JBSV22.11/1541.

P. D. Simon, J. Jiang, and L. K. Fryer, “Assessment of class participation in online and offline learning environments: a qualitative investigation of teachers’ best practices and challenges,” High. Educ. Res. Dev., vol. 44, no. 5, pp. 1191–1208, Jul. 2025, doi: 10.1080/07294360.2025.2462024.

A. Alkhateeb, A. M. M. Hezam, and A. A. Almuraikhi, “Assessing the use of AI tools for EFL exam preparation at Saudi universities: efficiency, benefits, and challenges,” Cogent Educ., vol. 12, no. 1, Dec. 2025, doi: 10.1080/2331186X.2025.2507553.

A. Sridhar and J. S. Rajshekhar, “AI-Integrated Proctoring System for Online Exams,” J. Artif. Intell. Capsul. Networks, vol. 4, no. 2, pp. 139–148, Jul. 2022, doi: 10.36548/jaicn.2022.2.006.

B. Erdem and M. Karabatak, “Cheating Detection in Online Exams Using Deep Learning and Machine Learning,” Appl. Sci., vol. 15, no. 1, p. 400, Jan. 2025, doi: 10.3390/app15010400.

J. S. Kumar, S. Anuar, and N. H. Hassan, “Transfer Learning based Performance Comparison of the Pre-Trained Deep Neural Networks,” Int. J. Adv. Comput. Sci. Appl., vol. 13, no. 1, pp. 797–805, 2022, doi: 10.14569/IJACSA.2022.0130193.

M. Hemis, H. Kheddar, S. Bourouis, and N. Saleem, “Deep learning techniques for hand vein biometrics: A comprehensive review,” Inf. Fusion, vol. 114, pp. 1–42, 2025, doi: 10.1016/j.inffus.2024.102716.

A. H. Ali, Mohanad G. Yaseen, Mohammad Aljanabi, and Saad Abbas Abed, “Transfer Learning: A New Promising Techniques,” Mesopotamian J. Big Data, vol. 2023, no. 3, pp. 29–30, Feb. 2023, doi: 10.58496/MJBD/2023/004.

X. Yu, H. Zhao, M. Zhang, Y. Wei, L. Zhou, and L. Ou, “DynamicAug: Enhancing Transfer Learning Through Dynamic Data Augmentation Strategies Based on Model State,” Neural Process. Lett., vol. 56, no. 3, pp. 1–27, 2024, doi: 10.1007/s11063-024-11626-9.

K. Lipianina-Honcharenko, M. Telka, and N. Melnyk, “Comparison of ResNet, EfficientNet, and Xception architectures for deepfake detection,” in Proceedings of the 1st International Workshop on Advanced Applied Information Technologies CEUR-WS, 2024, pp. 26–34.

A. Randive, “Comparative Study of Image Classification Models Using Deep Learning: MobileNet, ResNet, and EfficientNet,” Int. J. Sci. Res. Eng. Manag., vol. 09, no. 05, pp. 1–9, 2025, doi: 10.55041/ijsrem48167.

S. Essahraui et al., “Deep Learning Models for Detecting Cheating in Online Exams,” Comput. Mater. Contin., vol. 85, no. 2, pp. 3151–3183, 2025, doi: 10.32604/cmc.2025.067359.

T. Nur, Huzaeni, and M. Khadafi, “Implementasi Metode Object Detection Dengan Algoritma You Only Look Once (YOLO) Untuk Deteksi Kecurangan Di Dalam Ruang Ujian,” J. Teknol. Rekayasa Inf. dan Komput., vol. 6, no. 2, pp. 28–33, 2023.

A. Nur Aziz Thohari, M. Fathul Lathief, L. Triyono, and K. Santoso, “Deteksi Kecurangan Ujian Pada Ruangan Tertutup Menggunakan Algoritma YOLOv8,” J. Comput. Sci. Informatics Eng., vol. 4, no. 2, pp. 61–71, May 2025, doi: 10.55537/cosie.v4i2.1100.

E. Bimantoro, M. F. Hidayattullah, and D. I. Af’idah, “Learning Management System (LMS) Pada Kursus Online Berbasis Deteksi Kecurangan Ujian Menggunakan Model Mediapipe Face Mesh,” JIKO (Jurnal Inform. dan Komputer), vol. 8, no. 2, p. 268, 2024, doi: 10.26798/jiko.v8i2.1167.

F. B. Wicaksono and Y. Yamasari, “Pengembangan Model Pengawas Ujian Berbasis Kecerdasaan Buatan untuk Ujian Online,” J. Informatics Comput. Sci., vol. 6, no. 03, pp. 882–890, Jan. 2025, doi: 10.26740/jinacs.v6n03.p882-890.

M. P. Pangestu, S. Wiyono, and D. I. Af’idah, “Platform Ujian Online Berbasis Pendeteksi Gerakan Kecurangan Menggunakan Kamera,” Infomatek, vol. 26, no. 1, pp. 55–62, 2024, doi: 10.23969/infomatek.v26i1.11208.

M. I. Thohir, A. P. Iskandar, I. L. Kharisma, Kamdan, and A. Fergina, “Implementasi Deteksi Langsung Pada Sistem Ujian Online Menggunakan Algoritma Convolutional Neural Network,” J. CoSciTech (Computer Sci. Inf. Technol., vol. 5, no. 2, pp. 483–492, Sep. 2024, doi: 10.37859/coscitech.v5i2.7270.

E. Erik, S. G. Amalga, and S. N. Adzani, “Evaluasi UI/UX Aplikasi Web Deteksi Kecurangan Ujian Online Berbasis Video Dengan Sistem Usability Scale,” J. Pas. Inform., vol. 3, no. 1, Feb. 2024, doi: 10.23969/pasinformatik.v3i1.12545.

R. Setiawan, “OPTIMASI PENGALAMAN PENGGUNA DAN PROTOTYPING UNTUK PENILAIAN OTOMATIS DAN PENCEGAHAN KECURANGAN,” bit-Tech, vol. 7, no. 2, pp. 299–306, Dec. 2024, doi: 10.32877/bt.v7i2.1758.

A. T. Ginting, “Exam Cheating Dataset.” Accessed: Aug. 18, 2025. [Online]. Available: https://www.kaggle.com/datasets/ardutraagiginting/exam-cheating-dataset

I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning. MIT Press, 2016.

M. Sokolova and G. Lapalme, “A systematic analysis of performance measures for classification tasks,” Inf. Process. Manag., vol. 45, no. 4, pp. 427–437, 2009, doi: 10.1016/j.ipm.2009.03.002.

U. Rusmawan, I. Mulya, M. Sandy, A. Rahman, and P. Ramadhan, “Model Deteksi Kecurangan Ujian Menggunakan Pendekatan SURF-CNN Berdasarkan Data Citra Digital,” JSAI (Journal Sci. Appl. Informatics), vol. 8, no. 3, pp. 669–673, Nov. 2025, doi: 10.36085/jsai.v8i3.9383.