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{180559,
        author = {Sweta Chopda and Priyanka Sharma},
        title = {AI-Based Fake Image Detection using Digital Forensic Imaging Techniques},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {1},
        pages = {1674-1684},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=180559},
        abstract = {In recent years, the proliferation of AI-generated imagery has posed significant challenges to digital forensics and media authenticity verification. This paper presents a hybrid forensic AI system that combines deep learning with traditional forensic techniques to detect forged and computer-generated images. We propose a lightweight Convolutional Neural Network (CNN) based on MobileNetV2 architecture, trained to classify real and fake images. Additionally, we integrate Error Level Analysis (ELA), Photo-Response Non-Uniformity (PRNU), and metadata inconsistency checks to enhance decision accuracy. Our fusion model aggregates the outputs of all methods using a weighted average, providing an explainable and robust prediction. Experimental results show an accuracy improvement from 93% (CNN-only) to 95.6% with forensic fusion. The system operates efficiently on moderate hardware and supports visual forensics and report generation, making it suitable for real-world applications in journalism, law enforcement, and digital content verification.},
        keywords = {Deepfake Detection, Convolutional Neural Network, Error Level Analysis, PRNU, Metadata Tampering, Forensic Fusion.},
        month = {June},
        }