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{201030,
        author = {J. Veerendeswari and Thamizharasi R and Sangeetha M and Dharanya D},
        title = {Enhanced Hybrid Deep Learning for Detecting Deepfake Algorithm Using Blockchain Environment},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {no},
        pages = {184-191},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=201030},
        abstract = {Deepfake technology has emerged as a significant threat in digital media, enabling creation of highly realistic fake videos indistinguishable from authentic ones. This paper proposes an Enhanced Hybrid Deep Learning model integrated with a Blockchain-based Federated Learning (BFLDL) environment for effective deepfake detection. The system combines CNN and LSTM for spatial-temporal feature extraction, Capsule Networks (CN) for improved generalization, and a novel normalization technique for heterogeneous multi-source data. Transfer Learning (TL) accelerates training while blockchain ensures data integrity, privacy, and secure model aggregation. Experimental results on FaceForensics++, DeepFakeTIMIT, DFDCpre, and CelebDF demonstrate accuracy exceeding 97% across all benchmarks, outperforming state-of-the-art methods.},
        keywords = {Deepfake Detection, Hybrid Deep Learning, Blockchain, CNN, LSTM, Federated Learning, Capsule Networks, Transfer Learning, Privacy, Security},
        month = {May},
        }