Attention-Based Deep Learning Pipeline for AI-Created Image Recognition

Nadia Ali

doi:10.71229/jraa6834

Authors

Nadia Mahmood Ali Middle Technical University, Al-Mansour Medical Technical Institute, Baghdad, Iraq.

DOI:

https://doi.org/10.71229/jraa6834

Keywords:

AI-generated images, Deep learning, Attention mechanism, Image forensics, Synthetic media detection, Diffusion models

Abstract

The advent of generative AI models that can generate some of the most realistic images including DALL·E, Midjourney, and Stable Diffusion has posed a significant threat to digital forensics and media authenticity verifications. Conventional methods of forgery detection, which focus on splicing or copy-move manipulations, are not very efficient in the case of AI-generated images, which do not contain any explicit tampering traces. This paper presents Attention-Based Deep Learning Pipeline of AI-Created Image Recognition, intended to resolve the increasing challenge of separating AI-synthesized and authentic imagery. The proposed architecture incorporates three integrated branches, including low-level statistical feature extraction, high-level semantic representation learning, and attention-based feature refinement mechanism. The features that are extracted are combined and fed through a fully connected classifier to generate final predictions. The Synthbuster dataset that consists of images of several generative models, including DALL·E 2, DALL·E 3, Firefly, Glide, and versions of Stable Diffusion, were experimentally evaluated. The suggested framework score had an average AUC of 97.4%, as well as high accuracy, precision, recall, and F1-score. These findings support the robustness and generalization ability of the proposed model in detecting AI-generated images in a variety of generators and conditions.

References

[1] Y. Zhang, Z. Pang, S. Huang, C. Wang, and X. Zhou, “Unmasking AI-created visual content: A review of generated images and deepfake detection technologies,” 2025.

[2] M. Zabotka, “Distinguishing real from synthetic: Machine learning approaches for distinguishing AI-created images from photographs,” Ph.D. dissertation, Vilniaus Universitetas, 2025.

[3] S. Lakade, S. Khairkar, P. Kokane, A. Kale, and R. Mente, “Deep learning based detection of AI-generated synthetic images for digital forensics.”

[4] K. Harsanto, M. T. Zaidan, H. Lucky, and D. Suhartono, “Detecting AI-generated artworks with deep learning,” in Proc. 2024 Int. Conf. Informatics, Multimedia, Cyber and Information System (ICIMCIS), IEEE, 2024, pp. 472–476.

[5] D. Ghiurău and D. E. Popescu, “Distinguishing reality from AI: Approaches for detecting synthetic content,” Computers, vol. 14, no. 1, p. 1, 2024.

[6] D. Gragnaniello, F. Marra, and L. Verdoliva, “Detection of AI-generated synthetic faces,” in Handbook of Digital Face Manipulation and Detection, Cham: Springer, 2022, pp. 191–212.

[7] K. Man and J. Chahl, “A review of synthetic image data and its use in computer vision,” Journal of Imaging, vol. 8, no. 11, p. 310, 2022.

[8] S. S. Baraheem, T. N. Le, and T. V. Nguyen, “Image synthesis: A review of methods, datasets, evaluation metrics, and future outlook,” Artificial Intelligence Review, vol. 56, no. 10, pp. 10813–10865, 2023.

[9] A. Heidari, N. J. Navimipour, H. Dag, and M. Unal, “Deepfake detection using deep learning methods: A systematic and comprehensive review,” Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, vol. 14, no. 2, e1520, 2024.

[10] Z. Akhtar, “Deepfakes generation and detection: A short survey,” Journal of Imaging, vol. 9, no. 1, p. 18, 2023.

[11] Z. N. Ashani, I. S. C. Ilias, K. Y. Ng, M. R. K. Ariffin, A. D. Jarno, and N. Z. Zamri, “Comparative analysis of deepfake image detection methods using VGG16, VGG19 and ResNet50,” Journal of Advanced Research in Applied Sciences and Engineering Technology, vol. 47, no. 1, pp. 16–28, 2024.

[12] A. Malik, M. Kuribayashi, S. M. Abdullahi, and A. N. Khan, “Deepfake detection for human face images and videos: A survey,” IEEE Access, vol. 10, pp. 18757–18775, 2022.

[13] M. S. Rana, M. N. Nobi, B. Murali, and A. H. Sung, “Deepfake detection: A systematic literature review,” IEEE Access, vol. 10, pp. 25494–25513, 2022.

[14] G. Chen, C. Du, Y. Yu, H. Hu, H. Duan, and H. Zhu, “A deepfake image detection method based on a multi-graph attention network,” Electronics, vol. 14, no. 3, 2025.

[15] S. Y. Wang, O. Wang, R. Zhang, A. Owens, and A. A. Efros, “CNN-generated images are surprisingly easy to spot… for now,” in Proc. IEEE/CVF Conf. Computer Vision and Pattern Recognition (CVPR), 2020, pp. 8695–8704.

[16] O. Giudice, L. Guarnera, and S. Battiato, “Fighting deepfakes by detecting GAN DCT anomalies,” Journal of Imaging, vol. 7, no. 8, p. 128, 2021.

[17] J. Wang, K. Zeng, B. Ma, X. Luo, Q. Yin, G. Liu, and S. K. Jha, “GAN-generated fake face detection via two-stream CNN with PRNU in the wild,” Multimedia Tools and Applications, vol. 81, no. 29, pp. 42527–42545, 2022.

[18] B. Liu, F. Yang, X. Bi, B. Xiao, W. Li, and X. Gao, “Detecting generated images by real images,” in Proc. European Conf. Computer Vision (ECCV), Springer, 2022, pp. 95–110.

[19] D. C. Epstein, I. Jain, O. Wang, and R. Zhang, “Online detection of AI-generated images,” in Proc. IEEE/CVF Int. Conf. Computer Vision (ICCV), 2023, pp. 382–392.

[20] Y. Zhang and X. Xu, “Diffusion noise feature: Accurate and fast generated image detection,” arXiv preprint arXiv:2312.02625, 2023.

[21] I. Alam, M. S. Muneer, and S. S. Woo, “UGAD: Universal generative AI detector utilizing frequency fingerprints,” in Proc. 33rd ACM Int. Conf. Information and Knowledge Management (CIKM), 2024, pp. 4332–4340.

[22] D. Cozzolino, G. Poggi, R. Corvi, M. Nießner, and L. Verdoliva, “Raising the bar of AI-generated image detection with CLIP,” arXiv preprint arXiv:2312.00195, 2023.

[23] T. D. Nguyen, A. Azizpour, and M. C. Stamm, “Forensic self-descriptions for zero-shot detection, open-set source attribution, and clustering of AI-generated images,” in Proc. IEEE/CVF Conf. Computer Vision and Pattern Recognition (CVPR), 2025, pp. 3040–3050.

[24] Y. Li, Q. Bammey, M. Gardella, T. Nikoukhah, J. M. Morel, M. Colom, and R. G. Von Gioi, “MaskSim: Detection of synthetic images by masked spectrum similarity analysis,” in Proc. IEEE/CVF Conf. Computer Vision and Pattern Recognition (CVPR), 2024, pp. 3855–3865.

[25] Q. Bammey, “Synthbuster: Towards detection of diffusion model generated images,” IEEE Open Journal of Signal Processing, vol. 5, pp. 1–9, 2023.