Pengembangan Sistem Anti-Spoofing Berbasis Face Recognition Menggunakan Arsitektur YOLOv8n

Authors

  • Carmelita Angeline Tanujaya Institut Teknologi Kalimantan
  • Nur Fajri Azhar Institut Teknologi Kalimantan
  • Bowo Nugroho Institut Teknologi Kalimantan

DOI:

https://doi.org/10.52158/jacost.v6i2.1362

Keywords:

anti-spoofing, eye aspect ratio, facial landmark, face recognition, real-time, YOLOv8n

Abstract

Face spoofing poses a major threat to facial recognition–based authentication systems, especially in web-based environments that require lightweight and real-time verification. This study develops a real-time anti-spoofing system that integrates YOLOv8n for classifying four facial categories (real, printed, digital, and mask), combined with blink-based liveness verification using the Eye Aspect Ratio (EAR). Using 400,800 images and 18 videos, two training strategies—pretrained and from scratch—were evaluated. The pretrained model achieved a precision of 99.5%, recall of 98.6%, mAP50 of 99.4%, and mAP50–95 of 90.4%, slightly outperforming the from-scratch model. EAR threshold evaluation showed that a value of 0.17 yielded the best performance with 99.02% accuracy, 100% recall, a FAR of 16.11%, and an FRR of 0%. The proposed integration of YOLOv8n and EAR represents a practical novelty for lightweight, web-based anti-spoofing, providing fast inference and stable real-time performance suitable for modern facial authentication systems.

Downloads

Download data is not yet available.

References

[1] R. Budiarto Hadiprakoso and I. K. S. Buana, “Deteksi Serangan Spoofing Wajah Menggunakan Convolutional Neural Network,” Jurnal Teknik Informatika dan Sistem Informasi, vol. 7, no. 3, Dec. 2021, doi: 10.28932/jutisi.v7i3.4001.

[2] M. Alshaikhli, O. Elharrouss, S. Al-Maadeed, and A. Bouridane, “Face-Fake-Net: The Deep Learning Method for Image Face Anti-Spoofing Detection : 45,” in Proceedings - European Workshop on Visual Information Processing, EUVIP, Institute of Electrical and Electronics Engineers Inc., Jun. 2021. doi: 10.1109/EUVIP50544.2021.9484023.

[3] R. Ganjoo and A. Purohit, “Anti-Spoofing Door Lock Using Face Recognition and Blink Detection,” in Proceedings of the 6th International Conference on Inventive Computation Technologies, ICICT 2021, Institute of Electrical and Electronics Engineers Inc., Jan. 2021, pp. 1090–1096. doi: 10.1109/ICICT50816.2021.9358795.

[4] R. Vishnu, S. Vardhan, S. Varun, and N. R. Krishnamoorthy, “Detection of Anti-Spoofing Face Using Yolo,” vol. 7, no. 2, 2025, [Online]. Available: www.ijfmr.com

[5] H. Xing, S. Y. Tan, F. Qamar, and Y. Jiao, “Face Anti-Spoofing Based on Deep Learning: A Comprehensive Survey,” Jun. 01, 2025, Multidisciplinary Digital Publishing Institute (MDPI). doi: 10.3390/app15126891.

[6] A. Ali-Gombe, E. Elyan, C. Francisco Moreno-García, and J. Zwiegelaar, “Face detection with YOLO on edge,” vol. 3, pp. 284–292, 2021, doi: https://doi.org/10.1007/978-3-030-80568-5_24.

[7] Z. Yu et al., “Searching Central Difference Convolutional Networks for Face Anti-Spoofing.” [Online]. Available: https://github.com/ZitongYu/CDCN.

[8] A. Malik, M. Kuribayashi, S. M. Abdullahi, and A. N. Khan, “DeepFake Detection for Human Face Images and Videos: A Survey,” 2022, Institute of Electrical and Electronics Engineers Inc. doi: 10.1109/ACCESS.2022.3151186.

[9] A. Haliassos, K. Vougioukas, S. Petridis, and M. Pantic, “Lips Don’t Lie: A Generalisable and Robust Approach to Face Forgery Detection.”

[10] W. Lee, M. H. Kang, J. Song, and K. Hwang, “The design of preventive automated driving systems based on convolutional neural network,” Electronics (Switzerland), vol. 10, no. 14, Jul. 2021, doi: 10.3390/electronics10141737.

[11] A. Abdullah, G. A. Amran, S. M. A. Tahmid, A. Alabrah, A. A. AL-Bakhrani, and A. Ali, “A Deep-Learning-Based Model for the Detection of Diseased Tomato Leaves,” Agronomy, vol. 14, no. 7, Jul. 2024, doi: 10.3390/agronomy14071593.

[12] M. L. Hoang, “Smart Drone Surveillance System Based on AI and on IoT Communication in Case of Intrusion and Fire Accident,” Drones, vol. 7, no. 12, Dec. 2023, doi: 10.3390/drones7120694.

[13] “YOLOv5 vs. YOLOv8: A Detailed Comparison - Ultralytics YOLO Docs.” Accessed: Aug. 26, 2025. [Online]. Available: https://docs.ultralytics.com/compare/yolov5-vs-yolov8/

[14] “Explore Ultralytics YOLOv8 - Ultralytics YOLO Docs.” Accessed: Aug. 01, 2025. [Online]. Available: https://docs.ultralytics.com/models/yolov8/#supported-tasks-and-modes

[15] Husnan, C. Fatichah, and R. Dikairono, “Deteksi Objek Menggunakan Metode Yolo dan Implementasinya pada Robot Bawah Air,” vol. 12(3), Dec. 2023, doi: 10.12962/j23373539.v12i3.122326.

[16] W. Hutamaputra and F. Utaminingrum, “Implementasi Facial Landmark dalam Pengenalan Wajah pada Sistem Pembayaran Elektronik,” vol. 5, no. 5, pp. 2058–2064, May 2021, [Online]. Available: http://j-ptiik.ub.ac.id

[17] G. Amato, F. Falchi, C. Gennaro, and C. Vairo, “A Comparison of Face Verification with Facial Landmarks and Deep Features,” Apr. 2018. [Online]. Available: https://www.researchgate.net/publication/338048224

[18] C. Dewi, R. C. Chen, C. W. Chang, S. H. Wu, X. Jiang, and H. Yu, “Eye Aspect Ratio for Real-Time Drowsiness Detection to Improve Driver Safety,” Electronics (Switzerland), vol. 11, no. 19, Oct. 2022, doi: 10.3390/electronics11193183.

[19] C. Dewi, R. C. Chen, X. Jiang, and H. Yu, “Adjusting eye aspect ratio for strong eye blink detection based on facial landmarks,” PeerJ Comput Sci, vol. 8, 2022, doi: 10.7717/peerj-cs.943.

[20] “CelebA Spoof For Face AntiSpoofing.” Accessed: Aug. 26, 2025. [Online]. Available: https://www.kaggle.com/datasets/attentionlayer241/celeba-spoof-for-face-antispoofing

[21] “CelebA Spoof Dataset - Real People.” Accessed: Aug. 26, 2025. [Online]. Available: https://www.kaggle.com/datasets/trainingdatapro/celeba-spoof-dataset

[22] “iBeta 1 - 42,280 Liveness Detection Dataset.” Accessed: Aug. 26, 2025. [Online]. Available: https://www.kaggle.com/datasets/trainingdatapro/ibeta-level-1-liveness-detection-dataset-part-1

[23] “iBeta Level 2 Dataset, 33 000 attacks.” Accessed: Aug. 26, 2025. [Online]. Available: https://www.kaggle.com/datasets/tapakah68/pad-ibeta-level-2

[24] “Hispanic People - Liveness Detection Video Dataset.” Accessed: Aug. 26, 2025. [Online]. Available: https://www.kaggle.com/datasets/trainingdatapro/hispanic-people-liveness-detection-video-dataset

[25] “Black People - Liveness Detection Video Dataset.” Accessed: Aug. 26, 2025. [Online]. Available: https://www.kaggle.com/datasets/trainingdatapro/black-people-liveness-detection-video-dataset

[26] “Caucasian People - Liveness Detection Dataset.” Accessed: Aug. 26, 2025. [Online]. Available: https://www.kaggle.com/datasets/trainingdatapro/caucasian-people-liveness-detection-dataset

[27] “Anti Spoofing Real Dataset - 98,000 files.” Accessed: Aug. 26, 2025. [Online]. Available: https://www.kaggle.com/datasets/trainingdatapro/anti-spoofing-live

[28] “Silicone Mask Attack Dataset for Anti-Spoofing.” Accessed: Aug. 26, 2025. [Online]. Available: https://www.kaggle.com/datasets/axondata/silicone-mask-biometric-attack-dataset

[29] “Web Camera Face Liveness Detection - Face Dataset.” Accessed: Aug. 26, 2025. [Online]. Available: https://www.kaggle.com/datasets/trainingdatapro/web-camera-face-liveness-detection

[30] “On-Device Face Liveness Detection - Face Dataset.” Accessed: Aug. 26, 2025. [Online]. Available: https://www.kaggle.com/datasets/trainingdatapro/on-device-face-liveness-detection

[31] “Real VS Fake - Liveness Detection Dataset.” Accessed: Aug. 26, 2025. [Online]. Available: https://www.kaggle.com/datasets/trainingdatapro/real-vs-fake-anti-spoofing-video-classification

[32] “Silicone Masks Biometric Attacks Dataset.” Accessed: Aug. 26, 2025. [Online]. Available: https://www.kaggle.com/datasets/trainingdatapro/silicone-masks-biometric-attacks

[33] “Attacks with 2D Printed Masks of Indian People.” Accessed: Aug. 26, 2025. [Online]. Available: https://www.kaggle.com/datasets/trainingdatapro/attacks-with-2d-printed-masks-of-indian-people

[34] “Anti-Spoofing Dataset, 30,000 sets.” Accessed: Aug. 26, 2025. [Online]. Available: https://www.kaggle.com/datasets/tapakah68/anti-spoofing

[35] “Selfie and Video Dataset - Back Camera.” Accessed: Aug. 26, 2025. [Online]. Available: https://www.kaggle.com/datasets/tapakah68/selfie-and-video-on-back-camera

[36] “Full HD Videos - Liveness Detection Dataset.” Accessed: Aug. 26, 2025. [Online]. Available: https://www.kaggle.com/datasets/trainingdatapro/full-hd-webcam-live-attacks

[37] “2D Masks Presentation Attack Detection.” Accessed: Aug. 26, 2025. [Online]. Available: https://www.kaggle.com/datasets/trainingdatapro/real-people-and-attacks-with-2d-masks

[38] “Fake-Vs-Real-Faces (Hard).” Accessed: Aug. 26, 2025. [Online]. Available: https://www.kaggle.com/datasets/hamzaboulahia/hardfakevsrealfaces

[39] “IDR&D_train_set.” Accessed: Aug. 26, 2025. [Online]. Available: https://www.kaggle.com/datasets/nurmukhammed7/idrd-train-set

[40] E. Essel, F. Lacy, W. Elmedany, F. Albalooshi, and Y. Ismail, “Driver Drowsiness Detection Using Fixed and Dynamic Thresholding,” in 2022 International Conference on Data Analytics for Business and Industry, ICDABI 2022, Institute of Electrical and Electronics Engineers Inc., 2022, pp. 552–557. doi: 10.1109/ICDABI56818.2022.10041670.

Downloads

Published

2026-01-13

Issue

Vol. 6 No. 2 (2025): Desember 2025

Section

Articles

License

Copyright (c) 2025 Carmelita Angeline Tanujaya, Nur Fajri Azhar, Bowo Nugroho

Creative Commons License

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

Pernyataan Hak Cipta dan Lisensi

Dengan mengirimkan manuskrip ke Journal of Applied Computer Science and Technology (JACOST), penulis setuju dengan kebijakan ini. Tidak diperlukan persetujuan dokumen khusus.

  1. Hak cipta pada setiap artikel adalah milik penulis.
  2. Penulis mempertahankan semua hak mereka atas karya yang diterbitkan, tak terbatas pada hak-hak yang diatur dalam laman ini.
  3. Penulis mengakui bahwa Journal of Applied Computer Science and Technology (JACOST) sebagai yang pertama kali mempublikasikan dengan lisensi Creative Commons Atribusi 4.0 Internasional (CC BY-SA).
  4. Penulis dapat memasukan tulisan secara terpisah, mengatur distribusi non-ekskulif  dari naskah yang telah terbit di jurnal ini kedalam versi yang lain (misal: dikirim ke respository institusi penulis, publikasi kedalam buku, dll), dengan mengakui bahwa naskah telah terbit pertama kali pada Journal of Applied Computer Science and Technology (JACOST);
  5. Penulis menjamin bahwa artikel asli, ditulis oleh penulis yang disebutkan, belum pernah dipublikasikan sebelumnya, tidak mengandung pernyataan yang melanggar hukum, tidak melanggar hak orang lain, tunduk pada hak cipta yang secara eksklusif dipegang oleh penulis.
  6. Jika artikel dipersiapkan bersama oleh lebih dari satu penulis, setiap penulis yang mengirimkan naskah menjamin bahwa dia telah diberi wewenang oleh semua penulis bersama untuk menyetujui hak cipta dan pemberitahuan lisensi (perjanjian) atas nama mereka, dan setuju untuk memberi tahu rekan penulis persyaratan kebijakan ini.  Journal of Applied Computer Science and Technology (JACOST) tidak akan dimintai pertanggungjawaban atas apa pun yang mungkin timbul karena perselisihan internal penulis.

Lisensi :

Journal of Applied Computer Science and Technology (JACOST) diterbitkan berdasarkan ketentuan Lisensi Creative Commons Atribusi 4.0 Internasional (CC BY-SA). Lisensi ini mengizinkan setiap orang untuk :.

  • Adaptasi — menggubah, mengubah, dan membuat turunan dari materi ini untuk kepentingan apapun.

Lisensi :

  • Atribusi — Anda harus mencantumkan nama yang sesuai, mencantumkan tautan terhadap lisensi, dan menyatakan bahwa telah ada perubahan yang dilakukan. Anda dapat melakukan hal ini dengan cara yang sesuai, namun tidak mengisyaratkan bahwa pemberi lisensi mendukung Anda atau penggunaan Anda.

  • BerbagiSerupa — Apabila Anda menggubah, mengubah, atau membuat turunan dari materi ini, Anda harus menyebarluaskan kontribusi Anda di bawah lisensi yang sama dengan materi asli.

How to Cite

[1]
“Pengembangan Sistem Anti-Spoofing Berbasis Face Recognition Menggunakan Arsitektur YOLOv8n”, J. Appl. Comput. Sci. Technol., vol. 6, no. 2, pp. 149–161, Jan. 2026, doi: 10.52158/jacost.v6i2.1362.