A Comprehensive Review on Deep Learning Approaches for Classifying Real and AI generated Images

Due to the realm of the blooming generative models, like GANs, VAE and diffusion-based environment, the trustworthiness of authentication in visual media has been vastly challenged. AI-generated images appearing quite photorealistic go beyond human perceptual boundaries often overlying concerns for disinformation, digital tampering, forensic evidence authentication, and or the security of biometric purposes. This review organizes throughout the chronology of deep learning advancement to segregate real from synthetic images by focusing not much on its generalization snags, extraction of fake image or artifacts from sustainability in the aspect of datasets. Also this review provides systematic analysis on publicly available datasets and those essential research directions in the future being necessary to become a robust detection mechanism for fake images.

Deep Learning, AI-Generated Images, Diffusion Models, Image Forensics, Artifact Detection, Generalization, Convolutional Neural Networks (CNNs), Vision Transformers (ViT)

1. S. Mohammadjafari, “Improved 3D α GAN for Generating Connected Volumes,” arXiv preprint, 2022. [Google Scholar] [Crossref]

2. S. Sabnam, “Application of Generative Adversarial Networks in Image, Text-to-Image and Medical Imaging,” International Journal of Pattern Recognition and Artificial Intelligence, 2024. [Google Scholar] [Crossref]

3. D. Ruan, “Improvement of Generative Adversarial Network and Its Application to Bearing Fault Data Augmentation,” MDPI, 2023. [Google Scholar] [Crossref]

4. Z. Wang, T. Pang, C. Du, M. Lin, W. Liu, and S. Yan, “Better Diffusion Models Further Improve Adversarial Training,” arXiv preprint, 2023. [Google Scholar] [Crossref]

5. R. Huang, J. Han, G. Lu, X. Liang, Y. Zeng, W. Zhang, and H. Xu, “DiffDis: Empowering Generative Diffusion Model with Cross-Modal Discrimination Capability,” arXiv preprint, 2023. [Google Scholar] [Crossref]

6. A. Hatamizadeh, J. Song, G. Liu, J. Kautz, and A. Vahdat, “DiffiT: Diffusion Vision Transformers for Image Generation,” arXiv preprint, 2023. [Google Scholar] [Crossref]

7. S. Azizi, S. Kornblith, C. Saharia, M. Norouzi, and D. Fleet, “Synthetic Data from Diffusion Models Improves ImageNet Classification,” arXiv preprint, 2023. [Google Scholar] [Crossref]

8. K. Tian, Y. Jiang, Z. Yuan, B. Peng, and L. Wang, “Visual AutoRegressive Modeling: Scalable Image Generation via Next-Scale Prediction,” NeurIPS, 2024. [Google Scholar] [Crossref]

9. X. Tang, et al., “Image Generation Method Based on Improved Diffusion Models,” SPIE Conference on Computational Imaging, 2025. [Google Scholar] [Crossref]

10. Q. Yu, et al., “Randomized Autoregressive Visual Generation,” ICCV, 2025. [Google Scholar] [Crossref]

11. T. Li, et al., “Autoregressive Image Generation Without Vector Quantization via Diffusion Loss,” NeurIPS, 2024. [Google Scholar] [Crossref]

12. A. Kingma and M. Welling, “Auto-Encoding Variational Bayes,” ICLR, 2014. [Google Scholar] [Crossref]

13. K. Lipianina Honcharenko, M. Telka, and N. Melnyk, “Comparison of ResNet, EfficientNet, and Xception architectures for deepfake video detection,” CEUR Workshop Proc., vol. 3899, 2024. [Google Scholar] [Crossref]

14. B. Yasser, J. Hani, S. M. Elgayar, and O. Abdelhameed, “Deepfake Detection Using EfficientNet B4 and XceptionNet,” ICICIS / ResearchGate, 2024. [Google Scholar] [Crossref]

15. H. Lin, W. Luo, K. Wei, and M. Liu, “Improved Xception with Dual Attention Mechanism and Feature Fusion for Face Forgery Detection,” arXiv preprint, 2021. [Google Scholar] [Crossref]

16. A. Qadir et al., “An Efficient Deepfake Video Detection Using Pre trained ResNet CNN,” Journal / Elsevier, 2024. [Google Scholar] [Crossref]

17. V. D., J. S., G. J., and S. S., “Hybrid Deep Learning Approach for Deepfake Detection Using ResNet50 and EfficientNet B0,” IROIIP Journal, 2025. [Google Scholar] [Crossref]

18. D. Wodajo and S. Atnafu, “Deepfake Video Detection Using Convolutional Vision Transformer,” arXiv preprint, 2021. [Google Scholar] [Crossref]

19. Y.-J. Heo, et al., “Deepfake Detection Scheme Based on Vision Transformer and Distillation,” DeepAI, 2021. [Google Scholar] [Crossref]

20. A. Al Jallad, et al., “DFDT: An End-to-End DeepFake Detection Framework Using Vision Transformer,” Applied Sciences, vol. 12, no. 6, pp.2953, 2022. [Google Scholar] [Crossref]

21. P. M. Thuan, B. T. Lam, and P. D. Trung, “DSViT: An Enhanced Transformer Model for Deepfake Detection,” Journal of Science and Technology on Information Security, vol. 2, no. 22, 2024. [Google Scholar] [Crossref]

22. D. Nguyen, M. Astrid, E. Ghorbel, and D. Aouada, “FakeFormer: Efficient Vulnerability Driven Transformers for Generalisable Deepfake Detection,” arXiv preprint, 2024. [Google Scholar] [Crossref]

23. L. Zhao, M. Zhang, H. Ding, and X. Cui, “MFF Net: Deepfake Detection Network Based on Multi Feature Fusion,” Entropy, vol. 23, no. 12, p. 1692, 2021. MDPI+1 [Google Scholar] [Crossref]

24. “A Spatial-Frequency Aware Multi-Scale Fusion Network for Real-Time Deepfake Detection,” Fraunhofer, 2024. deepfake-demo.aisec.fraunhofer.de [Google Scholar] [Crossref]

25. “Two Stream Xception Structure Based on Feature Fusion for DeepFake Detection,” Int. J. Computational Intelligence Systems, vol.16, article 134, 2023. SpringerLink [Google Scholar] [Crossref]

26. “Multi-scale Deepfake Detection Method with Fusion of Spatial Features,” ECICE06 Journal, 2023. ECICE06 [Google Scholar] [Crossref]

27. X. Qiu, X. Miao, F. Wan, H. Duan, T. Shah, V. Ojhab, Y. Long, and R. Ranjan, “D2Fusion: Dual-domain Fusion with Feature Superposition for Deepfake Detection,” arXiv preprint, Mar. 2025. [Google Scholar] [Crossref]

• Predictive Health Monitoring Systems for Electric Vehicle Powertrains Using Edge AI and CAN Bus Data
• Internship Portals: A Systematic Review of Current Platforms and Future Directions
• Towards Better Urban Mobility: A Comprehensive Assessment of Pedestrian Infrastructure in Naval, Biliran Province, Philippines
• An Affordable and Sustainable Efficient Color Sorting System Using Arduino and TCS3200 Sensor
• Financial Stress and Mobility Patterns: Implication for Transportation Policy Among Jeepney Passengers