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{195852,
        author = {Gowthaman and Raju M and Jamsher N A and Nithish B A},
        title = {Deep Learning-Based AI Image Detection for Identifying Synthetic Images},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {1960-1965},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=195852},
        abstract = {The rapid advancement of artificial intelligence has significantly enhanced the capability of generative models to produce highly realistic images that are often indistinguishable from authentic photographs. While these developments offer numerous benefits across creative industries, healthcare visualization, entertainment, and research, they also introduce critical challenges such as misinformation, digital forgery, identity impersonation, and manipulation of visual evidence. Consequently, detecting AI-generated images has become essential for maintaining trust and authenticity in digital media. This paper proposes a deep learning-based AI image detection system designed to accurately classify images as real or synthetic. The proposed approach utilizes convolutional neural networks (CNNs) along with preprocessing techniques such as image resizing, normalization, and data augmentation to improve model performance and generalization. Transfer learning using pretrained architectures is also incorporated to enhance detection capability. The model is trained and evaluated on a diverse dataset consisting of real and AI-generated images. Performance is assessed using standard evaluation metrics including accuracy, precision, recall, and F1-score. Experimental results demonstrate that the proposed model achieves an accuracy of 94.2%, with high precision and recall, indicating its effectiveness in detecting synthetic images. The findings highlight the potential of deep learning techniques in addressing challenges related to digital forgery and media authenticity. The proposed system can be effectively applied in cybersecurity, digital forensics, and content verification systems to ensure reliability and trust in modern digital environments.},
        keywords = {AI Image Detection, Deep Learning, Convolutional Neural Networks, Image Forensics, Computer Vision, Deepfake Detection},
        month = {April},
        }