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{201038,
        author = {Mrs. J. Veerendeswari and Mr. Mohamed Thoufiq K and Mr. Prabanjan P and Mr. Mohamed Musthafa A and Mr.Gowsik Roshan V},
        title = {Efficiently Identifying Fake Audio and Video Using Transfer Learning},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {no},
        pages = {212-225},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=201038},
        abstract = {The rapid rise of deepfakes on social media threatens information integrity, public trust, and personal reputation. Existing detection systems lack transparency due to reliance on centralized storage mechanisms. This proposed system introduces a hybrid deepfake detection framework that combines multiple deep learning models for comprehensive analysis. VGG19 with CNN is used for image analysis, while LSTM and RNN models handle audio deepfake detection by capturing temporal inconsistencies. Video tampering is identified through a combination of RNN and CNN architectures, ensuring accurate spatial–temporal analysis. The system securely stores detection results within an internal database to maintain data consistency and controlled access. By integrating multimodal detection with secure storage, the model improves accuracy, reliability, and trust in deepfake detection across social media platforms while maintaining data integrity and accessibility.},
        keywords = {Deepfake Detection, VGG19, CNN, LSTM, RNN, Ethereum, Multimedia Forensics. I.},
        month = {May},
        }