Analisis Perbandingan Kinerja Arsitektur CNN VGG19, ResNet50, EfficientNetB0, dan MobileNetV2 untuk Deteksi Wajah Asli dan Wajah Buatan AI
Erika Yanti(1); Muhammad Faisal(2*); Titin Wahyuni(3); Abd Rakhim Nanda(4); Nurnawaty Nurnawaty(5); Rizki Yusliana Bakti(6);
(1) Informatika, Universitas Muhammadiyah Makassar, Makassar, Indonesia
(2) Informatika, Universitas Muhammadiyah Makassar, Makassar, Indonesia
(3) Informatika, Universitas Muhammadiyah Makassar, Makassar, Indonesia
(4) Teknik Pengairan, Universitas Muhammadiyah Makassar, Makassar, Indonesia
(5) Teknik Pengairan, Universitas Muhammadiyah Makassar, Makassar, Indonesia
(6) Informatika, Universitas Muhammadiyah Makassar, Makassar, Indonesia
(*) Corresponding Author
AbstractPerkembangan Generative Artificial Intelligence (GenAI) memungkinkan pembuatan citra wajah sintetis yang sangat menyerupai wajah asli, sehingga menimbulkan tantangan terhadap keaslian informasi digital, privasi, dan keamanan identitas. Penelitian ini mengevaluasi kinerja empat arsitektur Convolutional Neural Network (CNN), yaitu VGG19, ResNet50, EfficientNetB0, dan MobileNetV2, dalam klasifikasi wajah asli dan wajah hasil generasi AI. Dataset yang digunakan adalah HFD-8000 yang terdiri atas 8.000 citra wajah dengan skenario klasifikasi biner. Tahapan penelitian meliputi prapemrosesan data, pembagian dataset, augmentasi, penanganan ketidakseimbangan kelas, serta pelatihan model menggunakan transfer learning. Evaluasi dilakukan menggunakan accuracy, precision, recall, F1-score, ROC-AUC, dan confusion matrix. Hasil penelitian menunjukkan bahwa ResNet50 dan VGG19 memperoleh performa terbaik dengan akurasi 99,50% dan macro F1-score 99,22%. EfficientNetB0 mencapai akurasi 97,83% dan F1-score 96,61%, sedangkan MobileNetV2 memperoleh akurasi 92,58% dan F1-score 86,40%. Secara keseluruhan, ResNet50 menjadi model paling optimal karena menunjukkan keseimbangan antara akurasi, stabilitas, efisiensi, dan keandalan dalam klasifikasi wajah asli dan sintetis.
Keywordsdeepfake; Convolutional Neural Network; transfer learning; deteksi wajah; citra sintetis
|
Full Text:PDF |
Article MetricsAbstract view: 79 timesPDF view: 25 times |
Digital Object Identifier https://doi.org/10.33096/busiti.v7i2.3465
|
Cite |
References
S. M. Qureshi, A. Saeed, S. H. Almotiri, F. Ahmad, and M. A. A. Ghamdi, “Deepfake forensics: a survey of digital forensic methods for multimodal deepfake identification on social media,” PeerJ Comput. Sci., vol. 10, pp. 1–40, 2024, doi: 10.7717/PEERJ-CS.2037.
L. Y. Gong and X. J. Li, “A Contemporary Survey on Deepfake Detection: Datasets, Algorithms, and Challenges,” 2024, doi: 10.3390/electronics13030585.
G. Gupta, K. Raja, M. Gupta, T. Jan, S. T. Whiteside, and M. Prasad, “A Comprehensive Review of DeepFake Detection Using Advanced Machine Learning and Fusion Methods,” 2024. doi: 10.3390/electronics13010095.
A. Raza, K. Munir, and M. Almutairi, “A Novel Deep Learning Approach for Deepfake Image Detection,” Appl. Sci., vol. 12, no. 19, 2022, doi: 10.3390/app12199820.
V. L. L. Thing, “Deepfake Detection with Deep Learning: Convolutional Neural Networks versus Transformers,” in Proceedings of the 2023 IEEE International Conference on Cyber Security and Resilience, CSR 2023, 2023, pp. 246–253. doi: 10.1109/CSR57506.2023.10225004.
A. Angeline and H. Kusniyati, “Komparasi Performa VGG19, ResNet50, DenseNet121 dan MobileNetV2 Dalam Mendeteksi Gambar Deepfake,” CESS (Journal Comput. Eng. Syst. Sci., vol. 9, no. 2, p. 397, 2024, doi: 10.24114/cess.v9i2.58671.
Y. Lu and T. Ebrahimi, “Assessment framework for deepfake detection in real ‑ world situations,” EURASIP J. Image Video Process., vol. 8, 2024, doi: 10.1186/s13640-024-00621-8.
I. Balafrej and M. Dahmane, “Enhancing practicality and efficiency of deepfake detection,” Sci. Rep., vol. 14, no. 1, pp. 1–11, 2024, doi: 10.1038/s41598-024-82223-y.
Y. Ralhen and S. Sharma, “Enhanced deepfake detection using an ensemble of convolutional neural networks,” IAES Int. J. Artif. Intell., vol. 14, no. 5, pp. 4043–4049, 2025, doi: 10.11591/ijai.v14.i5.pp4043-4049.
L. Kroiß and J. Reschke, “Deepfake Detection of Face Images based on a Convolutional Neural Network,” 2025, [Online]. Available: http://arxiv.org/abs/2503.11389
E. Şafak and N. Barışçı, “Detection of fake face images using lightweight convolutional neural networks with stacking ensemble learning method,” PeerJ Comput. Sci., vol. 10, pp. 1–20, 2024, doi: 10.7717/PEERJ-CS.2103.
S. AlMuhaideb, H. Alshaya, L. Almutairi, D. Alomran, and S. T. Alhamed, “LightFakeDetect: A Lightweight Model for Deepfake Detection in Videos That Focuses on Facial Regions,” Mathematics, vol. 13, no. 19, pp. 1–22, 2025, doi: 10.3390/math13193088.
K. R. Ahmed, A. K. M. Masum, and M. Z. Uddin, “The HFD-8000,” Mendeley Data. [Online]. Available: https://data.mendeley.com/datasets/r88c3hr2x6/1
S. M. Yasir and H. Kim, “Lightweight Deepfake Detection Based on Multi-Feature Fusion,” Appl. Sci., vol. 15, no. 4, 2025, doi: 10.3390/app15041954.
A. Al-Adwan, H. Alazzam, N. Al-Anbaki, and E. Alduweib, “Detection of Deepfake Media Using a Hybrid CNN–RNN Model and Particle Swarm Optimization (PSO) Algorithm,” Computers, vol. 13, no. 4, pp. 1–16, 2024, doi: 10.3390/computers13040099.
S. Lei, J. Song, F. Feng, Z. Yan, and A. Wang, “Deepfake Face Detection and Adversarial Attack Defense Method Based on Multi-Feature Decision Fusion,” Appl. Sci., vol. 15, no. 12, 2025, doi: 10.3390/app15126588.
T. Raharjo et al., “Analisis Forensik Deepfake Berbasis Convolutional Neural Network (Cnn) Untuk Deteksi Inkonsistensi Tekstur Dan Pola Pada Citra Wajah,” JATI (Jurnal Mhs. Tek. Inform., vol. 9, no. 2, pp. 2731–2738, 2025, doi: 10.36040/jati.v9i2.13058.
A. Bhattacharjee et al., “CAE-Net: Generalized deepfake image detection using convolution and attention mechanisms with spatial and frequency domain features,” J. Vis. Commun. Image Represent., vol. 115, pp. 1–35, 2026, doi: 10.1016/j.jvcir.2025.104679.
T. N. Rohmah, P. Dewi, Kurniawati, H. Didin, M. A. Yunifa, and C.-C. Santiago, “Deepfake Image Detection using Deep Learning,” Int. J. Sci. Res. Eng. Manag., vol. 09, no. 05, pp. 1–9, 2025, doi: 10.55041/ijsrem46579.
E. M. Dharma, M. S. I. Ni, and P. R. A. A. I, “Deepfake Image Detection Using Convolutional Neural Network,” in Lecture Notes in Networks and Systems, 2025, pp. 51–62. doi: 10.1007/978-981-96-1981-8_5.
M. Amen and M. L. Ranam, “Lightweight Deepfake Detection on Mobile Devices Using Attention-Enhanced MobileNet and Frequency Domain Analysis,” J. Technol. Informatics Eng., vol. 4, no. 1, pp. 95–114, 2025, doi: 10.51903/jtie.v4i1.275.
A. Karathanasis, J. Violos, and I. Kompatsiaris, “A Comparative Analysis of Compression and Transfer Learning Techniques in DeepFake Detection Models,” Mathematics, vol. 13, no. 5, Mar. 2025, doi: 10.3390/math13050887.
M. Abbasi, P. Váz, J. Silva, and P. Martins, “Comprehensive Evaluation of Deepfake Detection Models: Accuracy, Generalization, and Resilience to Adversarial Attacks,” Appl. Sci., vol. 15, no. 3, pp. 1–16, 2025, doi: 10.3390/app15031225.
Refbacks
- There are currently no refbacks.
Copyright (c) 2026 Buletin Sistem Informasi dan Teknologi Islam (BUSITI)
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.