Deepfake Image Detection Using Transfer Learning Method
Abstract
The development of Artificial Intelligence (AI) technologies, particularly deep learning has led to the emergence of innovative applications such as deepfake technology, which enables the realistic manipulation of digital images and videos. While this technology offers positive applications in fields such as entertainment and education, it also poses significant risks of misuse, particularly in the dissemination of false information and violations of privacy. Therefore, deepfake detection has become a crucial aspect in preserving the authenticity of digital content. This study aims to analyze the effectiveness of transfer learning methods in detecting deepfake images using VGG16, VGG19, and ResNet50 architectures. The research employs a dataset of deepfake and real images sourced from Kaggle, comprising 10,826 facial images with a resolution of 256 × 256 pixels, evenly balanced between authentic and manipulated content. The data are split in an 80:20 ratio for training and testing purposes. Each model is trained using identical parameter configurations. The performance evaluation of the models was conducted using confusion matrix metrics, including accuracy, precision, recall, and F1-score. The results indicate that the VGG16 model achieved the best performance, with an accuracy of 76%, followed by VGG19 at 72%, and ResNet50 at 58%. VGG16 also outperformed the other models in terms of precision, recall, and F1-score, demonstrating more effective performance in identifying visual manipulation patterns. In contrast, ResNet50 exhibited the lowest performance, which may be attributed to its architectural complexity not being optimally aligned with the characteristics of the dataset. It can be concluded that the transfer learning approach using the VGG16 model is more effective in detecting deepfake images on this dataset. This study also highlights the importance of selecting appropriate architectures and fine-tuning models to the characteristics of the data.
Keywords
Full Text:
PDFReferences
[1] D. Purnamasari, D. Herlinudinkhaji, and Z. Mauludin, “Analisis Kualitas Citra Foveal Avascular Zone ( FAZ ) Dengan Teknik Kombinasi Pengacakan Piksel Jurnal Pepadun,” vol. 4, no. 3, pp. 325–333, 2023.
[2] D.Purnamasari, D.Herlinudinkhaji, and A.K.Dewi, “Foveal Avascular Zone (FAZ) Image Encryption Using Pixel Scrambling Combination Technique for Medical Image Security,” Infotel, vol. 16, no. 1, 2024, [Online]. Available: https://ejournal.ittelkom-pwt.ac.id/index.php/infotel/article/view/1029
[3] D. Purnamasari and N. Erwanti, “Enkripsi Citra Fovea Avascular Zone ( FAZ ) Menggunakan Kriptografi Vigener Cipher,” vol. 9, no. September, pp. 114–121, 2022.
[4] M. R. Shoaib, Z. Wang, M. T. Ahvanooey, and J. Zhao, “Deepfakes , Misinformation , and Disinformation in the Era of Frontier AI , Generative AI , and Large AI Models,” pp. 1–8, 2023.
[5] Regina Angelika Septi Rahayu;Handri Santoso, “ANALISIS GAMBAR WAJAH PALSU : MENDETEKSI KEASLIAN GAMBAR YANG DIMANIPULASI MENGGUNAKAN METODE VARIATIONAL AUTOENCODER DAN FORENSICS DEEP NEURAL NETWORK ANALYSIS OF FAKE FACE IMAGES : DETECTING THE AUTHENTICITY OF MANIPULATED IMAGES USING VARIATIONAL AUTOE,” vol. 2, no. 9, pp. 2701–2726, 2023.
[6] C. Gilbert and M. A. Gilbert, “Navigating the Dual Nature of Deepfakes : Ethical , Legal , and Technological Perspectives on Generative Artificial Intelligence AI ) Technology,” vol. 3, no. 10, 2024.
[7] N. Misirlis and H. Bin Munawar, “FROM DEEPFAKE TO DEEP-USEFUL : RISKS AND OPPORTUNITIES THROUGH A SYSTEMATIC LITERATURE REVIEW,” pp. 26–32, 2022.
[8] M. Indra, I. Nurtanio, and A. Achmad, “Deepfake detection in videos using Long Short-Term Memory and CNN ResNext,” vol. 14, no. 3, pp. 178–185, 2022.
[9] A. Heidari, N. J. Navimipour, and M. Unal, “Deepfake detection using deep learning methods : A systematic and comprehensive review,” no. August 2022, pp. 1–45, 2024, doi: 10.1002/widm.1520.
[10] S. M. Qureshi, A. Saeed, S. H. Almotiri, F. Ahmad, and M. A. Al Ghamdi, “Deepfake forensics : a survey of digital forensic methods for multimodal deepfake identification on social media,” pp. 1–40, 2024, doi: 10.7717/peerj-cs.2037.
[11] A. Hatem, S. Omnia, S. Hala, T. R. Ragab, and S. Mohsen, “Deepfake detection using convolutional vision transformers and convolutional neural networks,” Neural Comput. Appl., vol. 36, no. 31, pp. 19759–19775, 2024, doi: 10.1007/s00521-024-10181-7.
[12] S. Suratkar and F. Kazi, “Deep Fake Video Detection Using Transfer Learning Approach,” Arab. J. Sci. Eng., 2022, doi: 10.1007/s13369-022-07321-3.
[13] L. Boongasame, J. Boonpluk, S. Soponmanee, J. Muangprathub, and K. Thammarak, “Design and Implement Deepfake Video Detection Using VGG-16 and Long Short-Term Memory,” vol. 2024, 2024, doi: 10.1155/2024/8729440.
[14] V. Rajakumareswaran, S. Raguvaran, V. Chandrasekar, S. Rajkumar, and V. Arun, “Erode Sengunthar Engineering College , Tamil Nadu , Thuduppathi , India Sona College of Technology , Salem , India DEEPFAKE DETECTION USING TRANSFER LEARNING-BASED XCEPTION MODEL,” pp. 89–98, 2024.
[15] M. Kaur, S. Singh, and M. Kaur, “Computational Image Encryption Techniques: A Comprehensive Review,” Math. Probl. Eng., vol. 2021, no. i, 2021, doi: 10.1155/2021/5012496.
[16] A. V. Singh, D. Moghe, and K. Meenakshi, “Deepfake detection using fine-tuned VGG16 model : A transfer learning approach,” pp. 825–829, 2025, doi: 10.1201/9781003559085-141.
[17] F. Iqbal and U. A. Emirates, “Data Augmentation-based Novel Deep Learning Method for Deepfaked Images Detection Data Augmentation-based Novel Deep Learning Method for,” vol. 20, no. 11, 2026, doi: 10.1145/3592615.
[18] D. S. M. V, H. J. Vidyarani, G. Krishna, and S. Mohan, “Deep Fake Detection,” vol. 12, no. 9, pp. 298–305, 2024.
[19] B. Halima et al., “CRISP-MED-DM a Methodology of Diagnosing Breast Cancer,” vol. 9, no. 1, pp. 709–721, 2024.
[20] A. Rianti, N. Wachid, A. Majid, and A. Fauzi, “CRISP-DM : Metodologi Proyek Data Science,” pp. 107–114, 2023.
DOI: https://doi.org/10.18860/ijeie.v1i2.40796
Refbacks
- There are currently no refbacks.
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Gajayana Street 50 Malang 65144, Jawa Timur, Indonesia
This work is licensed under Creative Commons Attribution-ShareAlike 4.0 International
