Copyright © 2025 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{180376,
        author = {Sindhu M V and Thrupthi H R and Varsha U Nagesh and Sushmitha H K and Shashidhara H V},
        title = {Deep Learning-Based Detection of Fake Images and Video},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {1},
        pages = {1481-1488},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=180376},
        abstract = {The sophistication of artificially generated visual content has created unprecedented challenges for content authenticity verification in contemporary digital environments. Advanced computational models now produce synthetic imagery and video sequences with exceptional fidelity, creating substantial risks to information credibility across news media, political communication, and digital platforms. Conventional verification methodologies demonstrate limited effectiveness when confronting the nuanced characteristics of modern synthetic content generation. Contemporary developments in computational intelligence and neural network architectures have facilitated the creation of more robust and scalable authentication systems. This study introduces a hybrid identification framework that integrates spatial pattern recognition through convolutional architectures with sequential anomaly detection via memory-enhanced networks for video content analysis. The proposed system undergoes comprehensive training using multiple established benchmark collections including facial manipulation datasets, achieving superior performance in differentiating genuine content from artificially generated materials. This investigation highlights the importance of merging localized feature analysis with temporal consistency evaluation to advance synthetic content identification and strengthen digital information integrity.},
        keywords = {Synthetic Content Authentication, Convolutional Networks, Memory Networks, Generative Models, Digital Forensics, Content Manipulation Analysis},
        month = {June},
        }