21, February 2026

Deep Learning Approaches for Detecting AI-Generated Images

VOLUME-12; ISSUE-2; FEB-2026

Author(s): 1 Mr. Pragnesh Trivedi, 2 Dr. Brijesh Jajal,

Authors Affiliations:

1 Teaching Assistant, School of Computing & Technology, IAR University, Gandhinagar, India
2 Associate Professor, School of Computing & Technology, IAR University, Gandhinagar, India

DOIs:10.2015/IJIRMF/202602010     |     Paper ID: IJIRMF202602010


Abstract
Keywords
Cite this Article/Paper as
References
Abstract:    The rapid advancement of Artificial Intelligence has made it increasingly easy to generate highly realistic images using models such as GANs, DALL·E, and Stable Diffusion. While these AI-generated images have creative and commercial benefits, they also pose serious challenges for authenticity verification, media trust, and misinformation control. This research focuses on developing a deep learning-based system to distinguish between real and AI- generated images. A diverse dataset, including real-world photographs and AI- generated samples, will be curated from multiple sources. The proposed model combines Convolutional Neural Networks (CNNs) with Vision Transformers (ViTs) to capture both local and global features of images. Performance will be evaluated using metrics such as accuracy, precision, recall, and F1-score. The expected outcomes include a highly accurate detection system with robust generalization across different AI image generators. This study highlights the potential of deep learning for ensuring image authenticity and provides insights for applications in digital forensics, social media verification, and media literacy.    
Key Words:  AI generated image detection, fake image detection, GenAI images.

1 Mr. Pragnesh Trivedi, 2 Dr. Brijesh Jajal, (2026); Deep Learning Approaches for Detecting AI-Generated Images, International Journal for Innovative Research in Multidisciplinary Field, ISSN(O): 2455-0620, Vol-12, Issue-2, Available on –   https://www.ijirmf.com/

1. Popescu, A. C., & Farid, H. (2004). Exposing digital forgeries by detecting duplicated image regions.
IEEE Transactions on Signal Processing, 53(10), 758–767.
2. Goodfellow, I., Pouget-Abadie, J., Mirza, M., et al. (2014). Generative adversarial networks.
Communications of the ACM, 63(11), 139–144.
3. Zhou, P., Han, X., Morariu, V., & Davis, L. S. (2018). Two-stream neural networks for tampered face
detection. CVPR 2018 Workshops, 1831–1839
4. Marra, F., Gragnaniello, D., Verdoliva, L., & Poggi, G. (2019). Do GANs leave artificial fingerprints?
IEEE Signal Processing Letters, 26(7), 984–988.
5. Verdoliva, L. (2020). Media forensics and deepfakes: An overview. IEEE Journal of Selected Topics in
Signal Processing, 14(5), 910–932.
6. Ramesh, A., Dhariwal, P., Nichol, A., et al. (2022). Hierarchical text-conditional image generation with
CLIP latents (DALL·E 2). arXiv preprint arXiv:2204.06125.
7. Haliassos, A., Tzelepis, C., & Patras, I. (2022). Leveraging transformers for detecting GAN-generated
imagery. ICCV Workshops 2022.

Post Views: 136

Download Full Paper

Download PDF No. of Downloads:27 | No. of Views: 101