Download

This paper presents a new approach to recognizing synthesized images using transfer learning, specifically the VGG16 model. With the growing prevalence of AI-generated content on social media and the increasing use of synthesized images for fraudulent purposes, the ability to accurately distinguish between real and synthesized images is of utmost importance. The study addresses the limitations of existing image recognition technologies, which often have difficulty when working with high-quality images created by AI. The proposed method uses a custom-made dataset of more than 200 000 images, balanced between AI-generated and real images of several classes, to train the model. By fine-tuning the VGG16 model and unfreezing all layers, this approach achieves great accuracy. Experimental results show that the model achieves an overall accuracy of 97%, compared to 93% accuracy of baseline model, indicating its effectiveness in distinguishing between real and synthesized images. However, shortco-mings such as slight overfitting are noted, and suggestions for future improvement include regularization techniques and exploring more advanced architectures and techniques. This research highlights the potential of transfer learning in developing robust solutions for synthesized image recognition.

1. Wang, L.; Chei, W.; Yang, W.; Yu, F.R. A state-of-the-art review on image synthesis with generative adversarial networks. IEEE Access. 2020, 8, 63514-63537. https://doi.org/10.1109/ACCESS.2020.2982224

2. Huang, H.; Yu, P.S.; Wang, C. An introduction to image synthesis with generative adversarial nets. arXiv, 2018. [Online]. Available: https://arxiv.org/abs/1803.04469 (accessed 2024-05-24).

3. Huang, H.; Li, Z.; He, R.; Sun, Z.; Tan, T. Introvae: Introspective variational autoencoders for photographic image synthesis. Adv. Neural Inf. Process. Syst. 2018, 31.

4. Thies, J.; Zollhofer, M.; Niessner, M. Deferred neural rendering: Image synthesis using neural textures. ACM Trans. Graph. 2019, 38(4), 1-12. https://doi.org/10.1145/3306346.3323035

5. Esser, P.; Rombach, R.; Ommer, B. Taming transformers for high-resolution image synthesis. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021. https://doi.org/10.1109/CVPR46437.2021.01268

6. Jing, Y.; Yang, Y.; Feng, Z.; Ye, J.; Yu, Y.; Song, M. Neural style transfer: A review. IEEE Trans. Vis. Comput. Graphics 2019, 26(11), 3365-3385. https://doi.org/10.1109/TVCG.2019.2921336

7. Raza, A.; Munir, K.; Almutairi, M. A novel deep learning approach for deepfake image detection. Appl. Sci. 2022, 12 (19), 9820. https://doi.org/10.3390/app12199820

8. Sun, W.; Li, P.; Liang, Y.; Feng, Y.; Zhao, L. Detection of image artifacts using improved cas-cade region-based CNN for quality assessment of endoscopic images. Bioengineering. 2023, 10(11). https://doi.org/10.3390/bioengineering10111288

9. Makinde, F.L.; Tchamga, M.S.S.; Jafali, J.; Fatumo, S.; Chimusa, E.R.; Mulder, N.; Mazandu, G.K. Reviewing and assessing existing meta-analysis models and tools. Brief Bioinform. 2021, 11(22). https://doi.org/10.1093/bib/bbab324

10. Tao, R.; Zhao, X.; Li, W.; Li, H.-C.; Du, Q. Hyperspectral anomaly detection by fractional Fourier entropy. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2019, 12(12), 4920-4929. https://doi.org/10.1109/JSTARS.2019.2940278

11. Yang, Z.; Liang, J.; Xu, Y.; Zhang, X.-Y.; He, R. Masked relation learning for deepfake detec-tion. IEEE Trans. Inf. Forensics Security 2023, 18, 1696-1708. https://doi.org/10.1109/TIFS.2023.3249566

12. Dhar, A.; Prima, A.; Likhan, B.; Shemonti, A.; Abida, S. Detecting deepfake images using deep convolutional neural network; Brac University, 2021.

13. Bhatt, D.; Patel, C.; Talsania, H.; Patel, J.; Vaghela, R.; Pandya, S.; Modi, K.; Ghayvat, H. CNN variants for computer vision: History, architecture, application, challenges and future scope. Electronics. 2021, 10(20), 2470. https://doi.org/10.3390/electronics10202470

14. Yang, Q.; Zhang, Y.; Dai, W.; Pan, S.J. Transfer Learning. Cambridge University Press, 2020. https://doi.org/10.1017/9781139061773

15. Mascarenhas, S.; Agarwal, M. A comparison between VGG16, VGG19 and ResNet50 architec-ture frameworks for image classification. In CENTCON 2021, Proceedings of 2021 International Conference on Disruptive Technologies for Multi-Disciplinary Research and Applications, Bengaluru, India, 19-21 November, 2021, pp. 96-99. https://doi.org/10.1109/CENTCON52345.2021.9687944

16. Schettler, D. DiffusionDB-2M - Part 0001 to 0100 of 2000, 2023. [Online]. Available: https://www.kaggle.com/datasets/dschettler8845/diffusiondb-2m-part-0001-to-0100-of-2000 (accessed 2024-05-24).

17. Google Research. Open Images Dataset V7, 2020. [Online]. Available: https://storage.googleapis.com/openimages/web/index.html (accessed 2024-05-24).

18. Pang, B.; Nijkamp, E.; Wu, Y.N. Deep learning with TensorFlow: A review. J. Educ. Behav. Stat. 2020, 45(2), 227-248. https://doi.org/10.3102/1076998619872761

19. Dawani, J. Hands-On Mathematics for Deep Learning: Build a Solid Mathematical Foundation for Training Efficient Deep Neural Networks; Packt Publishing Ltd, 2020.

20. Kundu, N. Exploring ResNet50: An in-depth look at the model architecture and code implemen-tation, 2023. https://medium.com/@nitishkundu1993/exploring-resnet50-an-in-depth-look-at-the-model-architecture-and-code-implementation-d8d8fa67e46f (accessed 2024-05-24).

21. Koonce, B. Convolutional Neural Networks with Swift for TensorFlow: Image Recognition and Dataset Categorization; Apress, 2021, 109-123. https://doi.org/10.1007/978-1-4842-6168-2_10