International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | Zero-Trust Deepfake Detection Framework Using AI and Smart Contracts for Media Authentication |
|---|---|
| ABSTRACT | Recent advancements in artificial intelligence have made it possible to generate highly convincing deepfake images and videos, which pose serious threats to digital trust, data privacy, and information security. Deepfake content is increasingly misused for political manipulation, identity impersonation, cyber fraud, and tampering with legal evidence. Most existing deepfake detection solutions rely on centralized architectures, making them susceptible to privacy leakage, result manipulation, and lack of transparency.This paper presents a Blockchain-enabled Federated CNN–LSTM framework for reliable and privacy-aware deepfake detection. The proposed approach employs Convolutional Neural Networks (CNNs) to identify spatial manipulation artifacts within video frames and Long Short-Term Memory (LSTM) networks to capture temporal inconsistencies across consecutive frames. Federated Learning facilitates decentralized training without sharing raw video data, thereby ensuring privacy preservation, while Blockchain technology provides immutable and transparent storage of detection outcomes. Experimental results on standard benchmark datasets confirm that the proposed framework delivers improved detection accuracy, robustness, privacy protection, and trustworthiness compared to conventional deepfake detection approaches. |
| AUTHOR | PROF. SAURABH VERMA Department of Computer Science and Engineering, Baderia Global Institute of Engineering & Management, Jabalpur, Madhya Pradesh, India |
| VOLUME | 180 |
| DOI | DOI: 10.15680/IJIRCCE.2026.1401048 |
| pdf/48_Zero-Trust Deepfake Detection Framework Using AI and Smart Contracts for Media Authentication.pdf | |
| KEYWORDS | |
| References | [1] A. Rössler, D. Cozzolino, L. Verdoliva, C. Riess, J. Thies, and M. Nießner, “FaceForensics++: Learning to detect manipulated facial images,” in Proc. IEEE Int. Conf. Computer Vision (ICCV), Seoul, South Korea, 2019, pp. 1–11. [2] B. Dolhansky et al., “The DeepFake Detection Challenge (DFDC) Dataset,” arXiv preprint arXiv:2006.07397, 2020. [3] Y. Li, J. Bao, T. Zhang, H. Zhu, and X. Li, “Celeb-DF: A Large-Scale Challenging Dataset for DeepFake Forensics,” in Proc. IEEE/CVF Conf. Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA, 2020, pp. 3207–3216. [4] T. T. Nguyen, X. H. Nguyen, M. C. Nguyen, D. T. Nguyen, and S. Nahavandi, “Deep learning for deepfakes creation and detection: A survey,” Computer Vision and Image Understanding, vol. 223, pp. 103–118, 2022. [5] T. T. Nguyen, C. M. Nguyen, D. T. Nguyen, D. T. Nguyen, and S. Nahavandi, “Deepfake video detection using convolutional neural networks,” in Proc. IEEE Int. Conf. Systems, Man, and Cybernetics (SMC), Bari, Italy, 2019, pp. 1–6. [6] E. Sabir, J. Cheng, A. Jaiswal, W. AbdAlmageed, I. Masi, and P. Natarajan, “Recurrent convolutional strategies for face manipulation detection in videos,” arXiv preprint arXiv:1909.12424, 2019. [7] F. Chollet, “Xception: Deep learning with depthwise separable convolutions,” in Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA, 2017, pp. 1251–1258. [8] P. Zhou, X. Han, V. I. Morariu, and L. S. Davis, “Two-stream neural networks for tampered face detection,” in Proc. IEEE Conf. Computer Vision and Pattern Recognition Workshops (CVPRW), Honolulu, HI, USA, 2017, pp. 1831–1839. [9] S. Wang, O. Wang, R. Zhang, A. Owens, and A. A. Efros, “CNN-generated images are surprisingly easy to spot… for now,” in Proc. IEEE/CVF Conf. Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA, 2020, pp. 8695–8704. [10] S. Agarwal, H. Farid, Y. Gu, M. He, K. Nagano, and H. Li, “Protecting world leaders against deep fakes,” in Proc. IEEE Int. Conf. Image Processing (ICIP), Taipei, Taiwan, 2019, pp. 38–42. [11] S. Verma, M. Bhatele, and A. A. Waoo, “Enhancing medical image security through RGB and YUV color-based advanced triple watermarking techniques,” ResearchGate Publication, 2024. [12] S. Verma, M. Bhatele, and A. A. Waoo, “Role-based access control framework using dynamic watermarking for secure DICOM medical image communication,” ResearchGate / Journal Article, 2025. [13] S. Verma, M. Bhatele, and A. A. Waoo, “Advanced security framework for DICOM images using triple watermarking with DWT and SVD for role-based access control,” Research Article, 2025. [14] A. Hard, K. Rao, R. Mathews, et al., “Federated learning for mobile keyboard prediction,” Google AI Research, 2019. [15] A. Majeed and H. Kim, “Secure federated learning using blockchain-based consensus,” IEEE Access, vol. 8, pp. 227445–227456, 2020. [16] N. Mireshghallah, M. Nasr, R. Shokri, and A. Houmansadr, “Privacy-preserving deep learning with blockchain,” arXiv preprint arXiv:2005.09602, 2020. [17] S. Tariq, S. Lee, H. Lee, and S. Woo, “Blockchain-based secure video authentication,” IEEE Access, vol. 9, pp. 67423–67435, 2021. [18] Y. Liu, K. Zhang, J. Yang, and J. Deng, “Blockchain-enabled trust management in distributed artificial intelligence systems,” IEEE Internet of Things Journal, vol. 8, no. 12, pp. 9873–9885, 2021. |
