Detection of Diffusion-Generated Images Using CBAMEnhanced Pre-Trained CNNs

Abstract

AI-generated images have amplified the need for effective methods to distinguish between real and synthetic visuals. This underscores the need to develop new approaches to ensure data integrity and combat misinformation. While the existing literature predominantly focuses on Generative Adversarial Networks (GAN)-based synthetic images, researchers have largely overlooked the detection of diffusion-based models. This study fills this gap by demonstrating the potential of convolutional block attention module (CBAM)-enhanced convolutional neural networks (CNNs) for the effective detection of diffusion-based synthetic images. In this study, we use CNNs enhanced with the CBAM to propose a novel approach for detecting synthetic images. The CBAM-enhanced model, trained on the CIFAKE dataset, achieved a remarkable accuracy of 97.38% in detecting synthetic images. We integrate pre-trained CNN architectures, such as ResNet50 and DenseNet121, with a CBAM attention mechanism, which enhances performance by focusing on salient spatial and channel information. This approach presents a model that significantly enhances the detection capabilities for distinguishing fake images. Our findings contribute to the field of deepfake detection by providing a robust solution for automated digital image vetting, with implications for AI ethics, security, and broader societal discourse. The implementation details and source code are available at https://github.com/cmpe-dev/Fake-Detector-with-CBAM.

Keywords

• Synthetic data detection
• Diffusion model
• Pre-trained CNN
• CBAM
• CIFAKE

References

1. Agarwal, S., & Varshney, L. R. (2019). Limits of deepfake detection: A robust estimation viewpoint. arXiv preprint arXiv:1905.03493. https://doi.org/10.48550/arXiv.1905.03493 google scholar
2. Aghasanli, A., Kangin, D., & Angelov, P. (2023). Interpretable-through-prototypes deepfake detection for diffusion models. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 467–474. https://doi.org/10.1016/j.cvcv.2023 google scholar
3. Altuncu, E., Franqueira, V. N., & Li, S. (2024). Deepfake: Definitions, performance metrics and standards, datasets, and a meta-review. Frontiers in Big Data, 7, 1400024. https://doi.org/10.1016/j.fbd.2024.04.024 google scholar
4. Baraheem, S. S., & Nguyen, T. V. (2023). AI vs. AI: Can AI detect AI-generated images? Journal of Imaging, 9(10), 199. google scholar
5. Baraheem, S. S., Le, T.-N., & Nguyen, T. V. (2023). Image synthesis: A review of methods, datasets, evaluation metrics, and future outlook. Artificial Intelligence Review, 56(10), 10813–10865. https://doi.org/10.1016/j.artificialin.2023.10813 google scholar
6. Bird, J. J., & Lotfi, A. (2024). CIFAKE: Image classification and explainable identification of AI-generated synthetic images. IEEE Access, 12, 15642–15650. google scholar
7. Charitidis, P., Kordopatis-Zilos, G., Papadopoulos, S., & Kompatsiaris, I. (2020). Investigating the impact of pre-processing and prediction aggregation on the deepfake detection task. arXiv preprint arXiv:2006.07084. https://doi.org/10.48550/arXiv.2006.07084 google scholar
8. Corvi, R., Cozzolino, D., Zingarini, G., Poggi, G., Nagano, K., & Verdoliva, L. (2023). On the detection of synthetic images generated by diffusion models. In ICASSP 2023–IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 1–5). IEEE. google scholar

9. Dogan, Y., & Keles, H. Y. (2019). Stability and diversity in generative adversarial networks. Proceedings of the 27th Signal Processing and Communications Applications Conference (SIU). IEEE. google scholar
10. Dogan, Y. (2024). An innovative approach for parkinson’s disease diagnosis using CNN, NCA, and SVM. Neural Computing and Applications, 36(32), 20089-20110. google scholar
11. Dogan, Y. (2025). AutoEffFusionNet: A new approach for cervical cancer diagnosis using ResNet-based autoencoder with attention mechanism and genetic feature selection. IEEE Access, vol. 13, pp. 44107-44122. google scholar
12. Dolhansky, B., Howes, R., Pflaum, B., Baram, N., & Ferrer, C. C. (2019). The DeepFake Detection Challenge (DFDC) preview dataset. arXiv preprint arXiv:1910.08854. https://doi.org/10.1016/j.arXiv.2019.08.854. google scholar
13. Durall, R., Keuper, M., & Keuper, J. (2020). Watch your up-convolution: CNN based generative deep neural networks are failing to reproduce spectral distributions. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 7890–7899. https://doi.org/10.1016/j.cvpr.2020.10.1016 google scholar
14. Durall, R., Keuper, M., Pfreundt, F.-J., & Keuper, J. (2019). Unmasking deepfakes with simple features. arXiv preprint arXiv:1911.00686. google scholar
15. Frank, J., Eisenhofer, T., Schönherr, L., Fischer, A., Kolossa, D., & Holz, T. (2020). Leveraging frequency analysis for deep fake image recognition. In International Conference on Machine Learning (pp. 3247–3258). PMLR. google scholar
16. Gallagher, J., & Pugsley, W. (2024). Development of a dual-input neural model for detecting AI-generated imagery. arXiv preprint arXiv:2406.13688. google scholar
17. Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., & Bengio, Y. (2020). Generative adversarial networks. Communications of the ACM, 63(11), 139–144. google scholar
18. He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778. google scholar
19. Hossain, M. Z., Zaman, F. U., & Islam, M. R. (2023). Advancing AI-generated image detection: Enhanced accuracy through CNN and vision transformer models with explainable AI insights. In 2023 26th International Conference on Computer and Information Technology (ICCIT) (pp. 1–6). IEEE. google scholar
20. Huang, G., Liu, Z., Van Der Maaten, L., & Weinberger, K. Q. (2017). Densely connected convolutional networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4700–4708. google scholar
21. Islam, M. T., Lee, I. H., Alzahrani, A. I., & Muhammad, K. (2025). MexFiC: A meta ensemble explainable approach for artificial intelligence (AI)-synthesized fake image classification. Alexandria Engineering Journal, 116, 351–363. https://doi.org/10.1016/j.aej.2025.06.016 google scholar
22. Karras, T., Laine, S., & Aila, T. (2019). A style-based generator architecture for generative adversarial networks. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4401–4410. https://doi.org/10.1016/j.cvpr.2019.09.010. google scholar
23. Krizhevsky, A. (2024). The CIFAR-10 dataset. Retrieved December 10, 2024, from https://www.cs.toronto.edu/~kriz/cifar.html google scholar
24. Lalonde, J.-F., & Efros, A. A. (2007). Using color compatibility for assessing image realism. In 2007 IEEE 11th International Conference on Computer Vision (pp. 1–8). IEEE. google scholar
25. Li, H., Li, B., Tan, S., & Huang, J. (2020). Identification of deep network generated images using disparities in color components. Signal Processing, 174, 107616. https://doi.org/10.1016/j.signalprocessing.2020.10.1661 google scholar
26. Malik, A., Kuribayashi, M., Abdullahi, S. M., & Khan, A. N. (2022). Deepfake detection for human face images and videos: A survey. IEEE Access, 10, 18757–18775. https://doi.org/10.1016/j.ieaaccess.2022.02.057 google scholar
27. Nataraj L, Mohammed TM, Chandrasekaran S, Flenner A, Bappy JH, Roy-Chowdhury, A. K., & Manjunath, B. (2019). Detecting GAN generated fake images using co-occurrence matrices. arXiv preprint arXiv:1903.06836. google scholar
28. Nichol A, Dhariwal P, Ramesh A, Shyam P, Mishkin P, McGrew B, Sutskever, I., & Chen, M. (2021). GLIDE: Toward photorealistic image generation and editing with text-guided diffusion models. arXiv preprint arXiv:2112.10741. google scholar
29. Rossler, A., Cozzolino, D., Verdoliva, L., Riess, C., Thies, J., & Nießner, M. (2019). FaceForensics++: Learning to detect manipulated facial images. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 1–11. google scholar
30. Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015). ImageNet large scale visual recognition challenge. International Journal of Computer Vision, 115, 211–252. google scholar
31. Sandhya, A. & Kashyap, A. (2025). A statistical analysis for deepfake videos forgery traces recognition followed by a fine-tuned InceptionResNetV2 detection technique. Journal of Forensic Sciences, 70(1), 349–368. https://doi.org/10.1016/j.jfs.2025.07.016. google scholar
32. Simonyan, K., & Zisserman, K. (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556. google scholar
33. Sudarshana, K., & Vamsidhar, Y. (2025). UAM-Net: Robust deepfake detection through hybrid attention into scalable convolutional network. Expert Systems, 42(3), 70009. https://doi.org/10.1016/j.expertsystems.2025.07.009. google scholar
34. Tan, M., & Le, Q. (2021). EfficientNetV2: Smaller models and faster training. In International Conference on Machine Learning (pp. 10096–10106). PMLR. google scholar
35. Wang, D., Gao, F., Dong, J., & Wang, S. (2019). Change detection in synthetic aperture radar images based on convolutional block attention module. In 2019 10th International Workshop on the Analysis of Multitemporal Remote Sensing Images (MultiTemp) (pp. 1–4). IEEE. google scholar
36. Wang, T., Cheng, H., Chow, K. P., & Nie, L. (2023). Deep convolutional pooling transformer for deepfake detection. ACM Transactions on Multimedia Computing, Communications and Applications, 19(6), 1–20. google scholar
37. Wang, W., Tan, X., Zhang, P., & Wang, X. (2022). A CBAM based multiscale transformer fusion approach for remote sensing image change detection. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 15, 6817–6825. https://doi.org/10.1016/j.earthobserv.2022.02.016 google scholar
38. Wang, Y., Hao, Y., & Cong, A. X. (2024). Harnessing machine learning for discerning ai-generated synthetic images. arXiv preprint arXiv:2401.07358. google scholar
39. Woo, S., Park, J., Lee, J.-Y., & Kweon, I. S. (2018). CBAM: Convolutional block attention module. In Proceedings of the European Conference on Computer Vision (ECCV) (pp. 3–19). ECCV. google scholar
40. Yang, Z., Liang, J., Xu, Y., Zhang, X.-Y., & He, R. (2023). Masked relation learning for deepfake detection. IEEE Transactions on Information Forensics and Security, 18, 1696–1708. https://doi.org/10.1016/j.iefs.2024.06.016 google scholar
41. Yu, N., Davis, L. S., & Fritz, M. (2019). Attributing fake images to GANs: Learning and analyzing GAN fingerprints. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 7556–7566. google scholar
42. Yu, Y., Zhao, X., Ni, R., Yang, S., Zhao, Y., & Kot, A. C. (2023). Augmented multi-scale spatiotemporal inconsistency magnifier for generalized deepfake detection. IEEE Transactions on Multimedia, 25, 8487–8498. https://doi.org/10.1016/j.ietm.2024.04.016 google scholar
43. Zhang, X., Karaman, S., & Chang, S.-F. (2019). Detecting and simulating artifacts in GAN fake images. In 2019 IEEE International Workshop on Information Forensics and Security (WIFS) (pp. 1–6). IEEE. google scholar
44. Zhao, C., Wang, C., Hu, G., Chen, H., Liu, C., & Tang, J. (2023). ISTVT: Interpretable spatial-temporal video transformer for deepfake detection. IEEE Transactions on Information Forensics and Security, 18, 1335–1348. https://doi.org/10.1016/j.iefs.2023.1335 google scholar
45. Zhao, H., Liang, M., & Li, H. (2024). Research on gesture segmentation method based on FCN combined with CBAM-ResNet50. Signal, Image, and Video Processing, 18(11), 7729–7740. https://doi.org/10.1016/j.signal.2024.04.010. google scholar
46. Zhou, Y., Chen, Z., Li, P., Song, H., Chen, C. P., & Sheng, B. (2022). FSAD-Net: Feedback spatial attention dehazing network. IEEE Transactions on Neural Networks and Learning Systems, 34(10), 7719–7733. https://doi.org/10.1016/j.ienls.2022.02.017 google scholar