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{194294,
        author = {Ulthi Veerabhadrappa and Nagalli Chenna Kesava and Kulumala Alli Basha and Gujjala Naveen and S S Rajakumari and Dr. P Veeresh},
        title = {From Pixels To Provenance: Harnessing Source Camera Fingerprints To Detect AI-Created Images},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {10},
        pages = {3272-3278},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=194294},
        abstract = {The rapid advancement of generative artificial intelligence (AI) has revolutionized digital media creation, enabling the synthesis of highly realistic images that are virtually indistinguishable from authentic photographs. While these technologies empower creativity, they also pose significant challenges to digital forensics, misinformation detection, and intellectual property validation. This study introduces a Source Camera Fingerprint (SCF)-based Forensic Framework for detecting AI-generated images through intrinsic sensor pattern analysis. The proposed model leverages convolutional neural networks (CNNs) to extract photo-response non-uniformity (PRNU) patterns from authentic images and compares them with residual noise inconsistencies typical of generative models. Experimental results demonstrate that the SCF framework achieves 96.8% accuracy in distinguishing AI-created content from real photographs while maintaining interpretability through gradient-based visualization. This research bridges the gap between digital provenance verification and AI image forensics, ensuring authenticity in an increasingly synthetic visual world.},
        keywords = {AI Forensics, Image Authentication, Source Camera Fingerprint, Deep Learning, PRNU Analysis, Generative Models, Synthetic Media Detection.},
        month = {March},
        }