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{186359,
        author = {Susmit Acharya and Soma Chakraborty},
        title = {Prototype for Deepfake Detection and Content Authenticity for Small Digital Media Creators},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {6},
        pages = {1847-1853},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=186359},
        abstract = {The rapid evolution of deepfake technology has made synthetic image and video manipulation accessible to the general public, threatening the credibility of digital content and the livelihoods of small media creators. Existing deepfake detection systems, while effective in controlled or enterprise contexts, remain computationally intensive, and inaccessible to independent creators who lack high-performance infrastructure. This research investigates and develops a lightweight, AI-powered authenticity verification framework specifically designed for small digital content creators such as youtubers, educators, and independent filmmakers. By integrating techniques like spatial, temporal, and multimodal consistency analysis with resource-efficient architectures like MobileNet V3, the study aims to achieve real-time detection on consumer-grade hardware. The proposed system leverages open-source deepfake datasets such as FaceForensics++ and Celeb-DF to train and validate detection robustness under common real-world conditions such as compression, low resolution, and varied lighting. Furthermore, the framework introduces a user-centric interface that enables authenticity scoring. The experimental framework emphasizes a balance between accuracy, latency, and usability, thereby bridging the gap between academic deepfake forensic studies and the practical needs of independent creators. The outcome is a deployable framework and operational roadmap that democratizes content authenticity verification, contributing to digital trust and ethical media creation.},
        keywords = {Deepfake Detection, Content Authenticity, AI Forensics, Lightweight Neural Networks, Media Verification; Small Creators, Video Integrity, Algorithms, Machine Learning, Open-Source.},
        month = {November},
        }