Detecting Fake Images Generated by Artificial Intelligence Using Deep Learning Approach
Downloads
The rapid progress in artificial intelligence has enabled the creation of highly realistic images, leading to concerns about the credibility and genuineness of visual content. This study aims to address the growing challenge of verifying the authenticity of digital images in the era of advanced generative artificial intelligence by developing an effective method to detect AI-generated (deepfake) images. To achieve this objective, we employed a Machine Learning (ML) framework based on Convolutional Neural Networks (CNNs), evaluating five established architectures, VGG19, ResNet50, Xception, DenseNet-121, and InceptionV3, through a systematic pipeline involving dataset compilation, image preprocessing, feature extraction, model training, and rigorous validation. Our experimental analysis demonstrates that DenseNet-121 and InceptionV3 achieve state-of-the-art performance, both attaining 98% accuracy in distinguishing AI-synthesized images from real ones, despite a non-negligible error rate observed in other models. These findings highlight the viability of CNN-based approaches for reliable deepfake detection. The novelty of this work lies in its comparative assessment of multiple CNN architectures on a curated dataset of AI-generated imagery, offering practical insights into model selection for forensic and security applications. The proposed method contributes a robust, scalable solution with significant implications for digital content moderation, cybersecurity, and multimedia forensics, where timely and accurate identification of synthetic media is increasingly critical.
Downloads
[1] Topcu, A. E., Alzoubi, Y. I., Elbasi, E., & Camalan, E. (2023). Social Media Zero-Day Attack Detection Using TensorFlow. Electronics (Switzerland), 12(17), 3554. doi:10.3390/electronics12173554.
[2] Alzoubi, Y. I., Topcu, A. E., Elbasi, E., Buyukyilmaz, M., & Cibikdiken, A. O. (2024). Anticipate Movie Theme from Subtitle: A Deep Learning Approach. 2024 47th International Conference on Telecommunications and Signal Processing, TSP 2024, 205–210. doi:10.1109/TSP63128.2024.10605925.
[3] Akhtar, Z. (2023). Deepfakes Generation and Detection: A Short Survey. Journal of Imaging, 9(1), 18. doi:10.3390/jimaging9010018.
[4] Alzoubi, Y. I., Mishra, A., Topcu, A. E., & Cibikdiken, A. O. (2024). Generative Artificial Intelligence Technology for Systems Engineering Research: Contribution and Challenges. International Journal of Industrial Engineering and Management, 15(2), 169–179. doi:10.24867/IJIEM-2024-2-355.
[5] Alzoubi, Y. I., Topcu, A. E., & Erkaya, A. E. (2023). Machine Learning-Based Text Classification Comparison: Turkish Language Context. Applied Sciences (Switzerland), 13(16), 9428. doi:10.3390/app13169428.
[6] Shahzad, H. F., Rustam, F., Flores, E. S., Luís Vidal Mazón, J., de la Torre Diez, I., & Ashraf, I. (2022). A Review of Image Processing Techniques for Deepfakes. Sensors, 22(12), 4556. doi:10.3390/s22124556.
[7] Ali, A., Khan Ghouri, K. F., Naseem, H., Soomro, T. R., Mansoor, W., & Momani, A. M. (2022). Battle of Deep Fakes: Artificial Intelligence Set to Become a Major Threat to the Individual and National Security. 2022 International Conference on Cyber Resilience (ICCR), 1–5. doi:10.1109/iccr56254.2022.9995821.
[8] OpenAI (2026). OpenAI, San Francisco, United States. Available online: https://openai.com (accessed on May 2026).
[9] Tan, L., Wang, Y., Wang, J., Yang, L., Chen, X., & Guo, Y. (2023). Deepfake Video Detection via Facial Action Dependencies Estimation. Proceedings of the AAAI Conference on Artificial Intelligence, 37(4), 5276–5284. doi:10.1609/aaai.v37i4.25658.
[10] Midjourney (2026). Midjourney, San Francisco, United States. Available online: https://www.midjourney.com (accessed on May 2026).
[11] Hasan Abir, W., Rahman Khanam, F., Nabiul Alam, K., Hadjouni, M., Elmannai, H., Bourouis, S., Dey, R., & Monirujjaman Khan, M. (2023). Detecting Deepfake Images Using Deep Learning Techniques and Explainable AI Methods. Intelligent Automation & Soft Computing, 35(2), 2151–2169. doi:10.32604/iasc.2023.029653.
[12] Li, Y., Lyu, S. (2021). Obstructing DeepFakes by Disrupting Face Detection and Facial Landmarks Extraction. Deep Learning-Based Face Analytics. Advances in Computer Vision and Pattern Recognition. Springer, Cham, Switzerland. doi:10.1007/978-3-030-74697-1_12.
[13] Becker, C., & Laycock, R. (2023). Embracing deepfakes and AI-generated images in neuroscience research. European Journal of Neuroscience, 58(3), 2657–2661. doi:10.1111/ejn.16052.
[14] Han, R., Wang, X., Bai, N., Wang, Q., Liu, Z., & Xue, J. (2023). FCD-Net: Learning to Detect Multiple Types of Homologous Deepfake Face Images. IEEE Transactions on Information Forensics and Security, 18, 2653–2666. doi:10.1109/TIFS.2023.3269152.
[15] Guarnera, L., Giudice, O., Guarnera, F., Ortis, A., Puglisi, G., Paratore, A., Bui, L. M. Q., Fontani, M., Coccomini, D. A., Caldelli, R., Falchi, F., Gennaro, C., Messina, N., Amato, G., Perelli, G., Concas, S., Cuccu, C., Orrù, G., Marcialis, G. L., & Battiato, S. (2022). The Face Deepfake Detection Challenge. Journal of Imaging, 8(10), 263. doi:10.3390/jimaging8100263.
[16] Ramachandran, S., Nadimpalli, A. V., & Rattani, A. (2021). An Experimental Evaluation on Deepfake Detection using Deep Face Recognition. 2021 International Carnahan Conference on Security Technology (ICCST), 1–6. doi:10.1109/iccst49569.2021.9717407.
[17] Wang, J., Li, T., Luo, X., Shi, Y.-Q., & Jha, S. Kr. (2018). Identifying Computer Generated Images Based on Quaternion Central Moments in Color Quaternion Wavelet Domain. IEEE Transactions on Circuits and Systems for Video Technology, 29(9), 2775–2785. doi:10.1109/tcsvt.2018.2867786.
[18] Huang, B., Wang, Z., Yang, J., Ai, J., Zou, Q., Wang, Q., & Ye, D. (2023). Implicit Identity Driven Deepfake Face Swapping Detection. 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 4490–4499. doi:10.1109/cvpr52729.2023.00436.
[19] Heidari, A., Jafari Navimipour, N., Dag, H., & Unal, M. (2024). Deepfake detection using deep learning methods: A systematic and comprehensive review. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 14(2), 1520. doi:10.1002/widm.1520.
[20] Passos, L. A., Jodas, D., Costa, K. A. P., Souza Júnior, L. A., Rodrigues, D., Del Ser, J., Camacho, D., & Papa, J. P. (2024). A review of deep learning‐based approaches for deepfake content detection. Expert Systems, 41(8), e13570. doi:10.1111/exsy.13570.
[21] Byeon, H., Shabaz, M., Shrivastava, K., Joshi, A., Keshta, I., Oak, R., Singh, P. P., & Soni, M. (2024). Deep learning model to detect deceptive generative adversarial network generated images using multimedia forensic. Computers and Electrical Engineering, 113, 109024. doi:10.1016/j.compeleceng.2023.109024.
[22] Lagsoun, A.M., Oujaoura, M., Jraifi, A. (2025). Efficient Fusion of Machine Learning and Deep Learning for Enhanced Deepfake Detection in Compressed Videos. Intelligent Computing. CompCom 2025. Lecture Notes in Networks and Systems, Volume 1423. Springer, Cham, Switzerland. doi:10.1007/978-3-031-92602-0_39.
[23] Almalki, N. A., Ragab, M., & Kateb, F. (2025). Leveraging AI for Sustainable Deepfake Human Face Detection Using Transfer Learning Technique. 2025 22nd International Learning and Technology Conference (L&T), 228–232. doi:10.1109/lt64002.2025.10940123.
[24] Jin, W., Luo, H., & Tang, Y. (2025). Research on adversarial identification methods for AI-generated image software Craiyon V3. Journal of Forensic Sciences, 70(3), 1044–1056. doi:10.1111/1556-4029.70034.
[25] Kumar, B. A., Misra, N. K., Pathak, N., Ahmadpour, S. S., Krishnamoorthy, M., Shukla, D. K., Patidar, M., & Hakimi, M. (2025). Hybrid CMNV2: DeepFake faces classification and recognition using deep learning methods. Results in Engineering, 28. doi:10.1016/j.rineng.2025.107513.
[26] Wani, P., Chavan, S., Paithankar, S., Ghusse, D., & Barve, S. (2025). Comparative Analyais of CNN Architectures for Deep Fake Detection. 2025 3rd International Conference on Intelligent Systems, Advanced Computing and Communication (ISACC), 1119–1125. doi:10.1109/isacc65211.2025.10969171
[27] Whittaker, L., Kietzmann, T. C., Kietzmann, J., & Dabirian, A. (2020). “All around me are synthetic faces”: The mad world of AI-generated media. IT Professional, 22(5), 90–99. doi:10.1109/MITP.2020.2985492.
[28] Thaseen Ikram, S., V, P., Chambial, S., Sood, D., & V, A. (2023). A Performance Enhancement of Deepfake Video Detection through the use of a Hybrid CNN Deep Learning Model. International Journal of Electrical and Computer Engineering Systems, 14(2), 169–178. doi:10.32985/ijeces.14.2.6.
[29] Deepfake Detection Challenge Dataset (2026). Deepfake Detection Challenge Dataset, MetaAI, Menlo Park, United States. Available online: https://deepfakedetectionchallenge.ai (accessed on May 2026).
[30] Khalil, S. S., Youssef, S. M., & Saleh, S. N. (2021). iCaps-Dfake: An Integrated Capsule-Based Model for Deepfake Image and Video Detection. Future Internet, 13(4), 93. doi:10.3390/fi13040093.
[31] Kolagati, S., Priyadharshini, T., & Mary Anita Rajam, V. (2022). Exposing deepfakes using a deep multilayer perceptron – convolutional neural network model. International Journal of Information Management Data Insights, 2(1), 100054. doi:10.1016/j.jjimei.2021.100054.
[32] Kumar, M., Rai, P. K., & Kumar, P. (2024). A Novel Approach for Detecting Deepfake Face Using Machine Learning Algorithms. 2024 2nd International Conference on Disruptive Technologies (ICDT), 1588–1592. doi:10.1109/icdt61202.2024.10489036.
[33] Singh, A., Bharne, R., Kadu, R., Dasarwar, P. B., & Buddhawar, G. (2024). Impact of Deep Learning Techniques on Deep Fake Image Identification for Digital Investigation. 2024 International Conference on Modeling, Simulation & Intelligent Computing (MoSICom), 325–329. doi:10.1109/mosicom63082.2024.10881036.
[34] Keras (2026). Keras Applications, Keras, Carquefou, France. Available online: https://keras.io/api/applications/ (accessed on May 2026).
[35] Kaggle (2026). Deepfake and real images. Kaggle, San Francisco, United States. Available online: https://www.kaggle.com/datasets/manjilkarki/deepfake-and-real-images (accessed on May 2026).
[36] TensorFlow (2026). Module: tf.keras.applications, TensorFlow, Googleplex, California, United States. Available online: https://www.tensorflow.org/api_docs/python/tf/keras/applications/ (accessed on May 2026).
- This work (including HTML and PDF Files) is licensed under a Creative Commons Attribution 4.0 International License.
