Facial Deepfake Detection System Using YOLOv11 and Xception Architecture
DOI:
https://doi.org/10.30871/jaic.v10i4.13449Keywords:
Computer Vision, Deepfake, TensorFlow, Xception, YOLOv11Abstract
The rapid development of artificial intelligence has led to the emergence of deepfakes, which pose serious threats to information security and public trust in digital media. This study develops a facial deepfake detection system that integrates YOLOv11 for face detection and the Xception architecture for classifying real and manipulated faces. YOLOv11 successfully localized all facial regions in the tested dataset with high confidence scores. The Xception model achieved a testing accuracy of 90.10%, with a Recall of 97.11% for the Fake class and an AUC of 0.98. Visual explanation using Grad-CAM showed that the model focused on critical areas such as the forehead, temples, and face boundaries to detect manipulation artifacts. The system was implemented as a desktop application named "Snap Detector" and passed black-box testing. However, the average processing speed of 6.26 FPS on an NVIDIA T4 GPU indicates that further optimization is needed for real-time performance.
Downloads
References
[1] T. T. Nguyen et al., “Deep learning for deepfakes creation and detection: A survey,” Computer Vision and Image Understanding, vol. 223, p. 103525, Oct. 2022, doi: 10.1016/J.CVIU.2022.103525.
[2] Z. Shen et al., “A Survey of the Past, Present, and Future of Erasure Coding for Storage Systems,” ACM Transactions on Storage, vol. 21, no. 1, p. 39, Jan. 2025, doi: 10.1145/3708994.
[3] A. A. Khan, A. A. Laghari, S. A. Inam, S. Ullah, M. Shahzad, and D. Syed, “A survey on multimedia-enabled deepfake detection: state-of-the-art tools and techniques, emerging trends, current challenges & limitations, and future directions,” Discover Computing 2025 28:1, vol. 28, no. 1, pp. 48-, Apr. 2025, doi: 10.1007/S10791-025-09550-0.
[4] N. B. P. Athallah, A. Candra, and H. A. Sanusi, “Urgensi dan Kecukupan Pengaturan Deepfake dalam Undang-Undang Informasi dan Transaksi Elektronik di Indonesia,” Judge : Jurnal Hukum , vol. 6, no. 09, pp. 1665–1676, Apr. 2026, doi: 10.54209/JUDGE.V6I09.2279.
[5] S. W. Nurdin and I. F. Nugraha, “Ancaman Deepfake Dan Disinformasi Berbasis Ai: Implikasi Terhadap Keamanan Siber Dan Stabilitas Nasional Indonesia,” JIMR : Journal Of International Multidisciplinary Research, vol. 4, no. 01, pp. 73–92, Jun. 2025, doi: 10.62668/JIMR.V4I01.1551.
[6] T. Raharjo et al., “Analisis Forensik Deepfake Berbasis Convolutional Neural Network (CNN) Untuk Deteksi Inkonsistensi Tekstur dan Pola Pada Citra Wajah,” JATI (Jurnal Mahasiswa Teknik Informatika), vol. 9, no. 2, pp. 2731–2738, Mar. 2025, doi: 10.36040/JATI.V9I2.13058.
[7] C. R. Gunawan, N. Nurdin, and F. Fajriana, “Deteksi Ikan Segar Secara Realtime dengan YOLOv4 menggunakan Metode Convolutional Neural Network,” J. Komtika (Komputasi dan Inform., vol. 7, no. 1, pp. 1–11, May 2023, doi: 10.31603/komtika.v7i1.8986.
[8] S. Adventino Gulo, A. Amelia Pertiwi, S. Putri Syaifullah Nasution, and H. Syahputra, “Deteksi Deepfake Dalam Citra Menggunakan Convolutional Neural Network (Cnn),” JATI (Jurnal Mahasiswa Teknik Informatika), vol. 9, no. 5, pp. 8655–8660, 2025, doi: 10.36040/jati.v9i5.14896.
[9] R. P. Pahlevi and M. Ma’sumah, “Deteksi Deepfake Pada Citra Biometrik Wajah Menggunakan Yolov9 Dan Convolutional Neural Network (Cnn),” Conference on Innovation and Application of Science and Technology (CIASTECH), vol. 8, no. 1, pp. 559–567, Jan. 2025, doi: 10.31328/CIASTECH.V8I1.7518.
[10] L. M. Al Ikhlas, D. Abdullah, and N. Nurdin, “Environmental Image Analysis for Smoke-Free Area Compliance Mapping Using YOLOv11 and Geographic Information Systems”, JAIC, vol. 10, no. 3, pp. 3034–3045, Jun. 2026.
[11] Y. J. Fan et al., “Machine Learning: Using Xception, a Deep Convolutional Neural Network Architecture, to Implement Pectus Excavatum Diagnostic Tool from Frontal-View Chest X-rays,” Biomedicines 2023, Vol. 11, Page 760, vol. 11, no. 3, p. 760, Mar. 2023, doi: 10.3390/BIOMEDICINES11030760.
[12] J. Ulfah and N. Nurdin, “Implementasi Metode Deteksi Tepi Canny Untuk Menghitung Jumlah Uang Koin Dalam Gambar Menggunakan Opencv,” J. Inform. dan Tek. Elektro Terap., vol. 11, no. 3, Aug. 2023, doi: 10.23960/jitet.v11i3.3147.
[13] A. Ilyana, N. Nurdin, and M. Maryana, “Real-Time Detection of Coffee Cherry Ripeness Using YOLOv11,” J. Appl. Informatics Comput., vol. 9, no. 4, pp. 1170–1178, 2025
[14] J. Ulfah, M. Ula, F. Fajriana, and N. Nurdin, “Analisis Perbandingan Kinerja Algoritma You Only Look Once ( YOLOv8 ) Dan Single Shot Detector ( SSD ) dalam Pengenalan Nominal Uang Kertas,” Journal of Artificial Intelligence and Software Engineering, vol. 4, no. 2, 2024, doi: 10.30811/jaise.v5i4.7471.
[15] J. Huang, K. Wang, Y. Hou, and J. Wang, “LW-YOLO11: A Lightweight Arbitrary-Oriented Ship Detection Method Based on Improved YOLO11,” Sensors 2025, Vol. 25, Page 65, vol. 25, no. 1, p. 65, Dec. 2024, doi: 10.3390/S25010065.
[16] C. R. Gunawan, N. Nurdin, and F. Fajriana, “Design of a Real-Time Object Detection Prototype System with YOLOv3 (You Only Look Once),” Int. J. Eng. Sci. Inf. Technol., vol. 2, no. 3, pp. 96–99, 2022.
[17] L. He, Y. Zhou, L. Liu, and J. Ma, “Research and Application of YOLOv11-Based Object Segmentation in Intelligent Recognition at Construction Sites,” Buildings 2024, Vol. 14, Page 3777, vol. 14, no. 12, p. 3777, Nov. 2024, doi: 10.3390/BUILDINGS14123777.
[18] C. Kwan, B. Li, L. Yu Gong, and X. Jun Li, “A Contemporary Survey on Deepfake Detection: Datasets, Algorithms, and Challenges,” Electronics 2024, Vol. 13, Page 585, vol. 13, no. 3, p. 585, Jan. 2024, doi: 10.3390/ELECTRONICS13030585.
[19] M. Iman, H. R. Arabnia, and K. Rasheed, “A Review of Deep Transfer Learning and Recent Advancements,” Technologies 2023, Vol. 11, Page 40, vol. 11, no. 2, p. 40, Mar. 2023, doi: 10.3390/TECHNOLOGIES11020040.
[20] Z. Wang, Q. Liu, and J. Zhang, “Small Object Detection Enhancement in YOLO Networks for Surveillance Applications,” Pattern Recognit. Lett., vol. 172, pp. 45–53, 2024.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Fachril Akbar, Nurdin Nurdin, Kurniawati Kurniawati
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (Attribution-ShareAlike 4.0 International (CC BY-SA 4.0) ) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
