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{199577,
        author = {Kushal H M and Rachan M and Supreet Mujagonnavar and Apurva Patil and Prof. N P Nethravathi},
        title = {TrueSightLens: An AI-Based Deepfake Video Detection System. Multimodal Fusion of Visual Artifacts, Temporal Dynamics, and Lip-Sync Inconsistency},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {12766-12773},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=199577},
        abstract = {The rapid evolution of Artificial Intelligence has led to the emergence of deepfake videos, which pose significant threats to digital authenticity, including misinformation, identity fraud, and cybercrime. This paper presents TrueSightLens, an AI-based deepfake detection system that combines spatial, temporal, and audio-visual analysis for robust and scalable detection. The proposed approach employs a Convolutional Neural Network (CNN) for spatial feature extraction and a Bidirectional Gated Recurrent Unit (BiGRU) for temporal sequence modeling. To further improve reliability, the system incorporates an audio-visual lip-synchronization module that measures temporal alignment between the speech signal and lip-motion dynamics to detect cross-modal inconsistencies, which are strong indicators of manipulated or synthesized video content. TrueSightLens is implemented using a full-stack architecture with a React frontend, Node.js backend, and a Python-based AI engine. Experimental results indicate that multimodal analysis improves detection performance and robustness compared with single-modality methods. The system also provides explainable outputs through Grad-CAM visualizations, improving interpretability and user trust.},
        keywords = {Deepfake Detection, CNN, GRU, Computer Vision, Artificial Intelligence, Multimedia Forensics, Explainable AI},
        month = {April},
        }