Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{177633,
        author = {Juhi Singh and ADITI SINGH and RAGHURAJ SINGH and MILLAN SAXENA},
        title = {Improving Fake Image Detection with the Power of Transfer Learning and CNN},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {12},
        pages = {1136-1140},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=177633},
        abstract = {Artificial Intelligence (AI) generated fake Images are becoming more common day by day and it is very hard to differentiate them from the real ones. In this study, an efficient and reliable technique to detect AI generated images has been proposed by using a strong pre-trained model and fine-tuning it as per the required domain. We apply a deep learning based approach to help improve the detection of these AI generated synthetic images by using transfer learning with the well-known VGG16 model originally trained on the CIFAR-10 dataset [7]. To boost the performance of the technique, it is enhanced by adding extra layers, dropout, and batch normalization. The improved version of VGG16 achieved an impressive 95.90% validation accuracy, along with high precision and recall.},
        keywords = {AI-generated images, CNN-based image classification, deep learning, transfer learning, VGG16 model.},
        month = {May},
        }