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{202671,
        author = {Riya Kaushal and Mandisha Mirza and Reeti Shrimal and Radhika Kumawat and Priyanka Chirote and Kavita Namdev},
        title = {AuthenX: A Multi-Modal Deep Learning Framework for Multimedia Authentication and Automated Fact- Checking},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {12},
        pages = {12574-12584},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=202671},
        abstract = {Increased accessibility of Generative AI has brought a surge in the number of manipulated media. Detection methods, however, are usually tailored to individual modalities, rendering them ineffective against real-world instances that involve various content types in a piece of misinformation. AuthenX is a multi-modal pipeline that unites image, video, text, and headlines verification. Rather than developing another independent detection module, we emphasize architectural integration of independently verified parts. Specifically, the image and video modules utilize shared architecture based on EfficientNet-B4, followed by frame-wise concatenation; the text detection part involves weighted combination of perplexity, burstiness, and stylometry models; finally, the claim verification component performs a real-time web search and calculates semantic similarity via lightweight transformer-based embeddings. An important contribution of our work is that the resulting framework can be considered not only from a methodological but also from a system perspective, as it includes stateless authentication and scoped user persistence features, allowing for longitudinal verification tracking. Experimental evidence shows that the proposed solution exhibits a balance between efficiency and effectiveness of multi-modal detection.},
        keywords = {Deep fake Detection, Multimedia Authentication, Fake News Detection, CNN, NLP, Fact Checking, Digital Forensics, AI Security.},
        month = {May},
        }