This project proposes a Multimodal Ensemble-Based Fake Media Detection Framework to identify fake and AI-generated content across text, image, audio, and video. It addresses the growing threat of deepfakes and misinformation caused by generative AI. The system uses TF-IDF–based machine learning for text classification. Transformer-based models are applied for image and audio deepfake detection. Video analysis combines frame and audio verification through multimodal fusion. Ensemble majority voting improves accuracy and reduces model bias. Experimental results show higher performance compared to single-modality models. The system is deployed as a real-time web application for practical media authentication.

The proposed Multimodal Ensemble-Based Fake Media Detection Framework effectively identifies fake and AI-generated content across text, image, audio, and video modalities. By integrating ensemble majority voting and confidence aggregation, the system improves accuracy and reduces model bias compared to unimodal approaches. Experimental results confirm that multimodal fusion enhances robustness and reliability. Overall, the framework provides a scalable and practical solution for real-time media authentication and combating AI-generated misinformation. Furthermore, the modular architecture allows easy integration of advanced deep learning models as generative technologies evolve.

(Periodical style) [1] H. Allcott and M. Gentzkow, “Social media and fake news in the 2016 election,” Journal of Economic Perspectives, vol. 31, no. 2, pp. 211–236, 2017. [2] K. Shu, A. Sliva, S. Wang, J. Tang, and H. Liu, “Fake news detection on social media: A data mining perspective,” ACM SIGKDD Explorations Newsletter, vol. 19, no. 1, pp. 22–36, 2017. [3] H. Nguyen, J. Yamagishi, and I. Echizen, “Deep learning for deepfakes creation and detection: A survey,” Computer Vision and Image Understanding, vol. 223, 2022. (Book style) [4] C. M. Bishop, Pattern recognition and machine learning. New York, NY, USA: Springer, 2006. [5] I. Goodfellow, Y. Bengio, and A. Courville, Deep learning. Cambridge, MA, USA: MIT Press, 2016. [6] D. Jurafsky and J. H. Martin, Speech and language processing, 3rd ed. Upper Saddle River, NJ, USA: Pearson, 2021. (Book style with paper title and editor) [7] M. Todisco, X. Wang, V. Vestman, et al., “ASVspoof 2019: Future horizons in spoofed and fake audio detection,” in Interspeech 2019 proceedings, G. Kubin and Z. Kacic, Eds. Graz, Austria: ISCA, 2019, pp. 1008–1012. [8] A. Rössler, D. Cozzolino, L. Verdoliva, C. Riess, J. Thies, and M. Nießner, “FaceForensics++: Learning to detect manipulated facial images,” in Computer vision – ICCV 2019 workshops, L. Leal-Taixé and S. Roth, Eds. Cham, Switzerland: Springer, 2020, pp. 1–11. (Published Conference Proceedings style) [9] H. Ahmed, I. Traore, and S. Saad, “Detecting opinion spams and fake news using text classification,” in Proc. 2017 IEEE Int. Conf. Comput. Sci. Eng. (CSE) and IEEE Int. Conf. Embedded Ubiquitous Comput. (EUC), Guangzhou, China, 2017, pp. 1–6. [10] W. Y. Wang, “Liar, liar pants on fire: A new benchmark dataset for fake news detection,” in Proc. 55th Annu. Meeting Assoc. Comput. Linguistics (ACL), Vancouver, Canada, 2017, pp. 422–426. (Thesis or Dissertation style) [11] K. Shu, “Fake news detection on social media: Data mining perspective,” Ph.D. dissertation, Dept. Comput. Sci., Arizona State University, Tempe, AZ, USA, 2019. [12] N. Ruchansky, “Hybrid deep learning models for fake news detection,” M.S. thesis, Dept. Comput. Sci., Arizona State University, Tempe, AZ, USA, 2017. (Patent style) [13] J. Smith and R. Kumar, “System and method for detecting fake news using machine learning,” U.S. Patent 10 123 456, Jan. 15, 2019. [14] M. Johnson, L. Wang, and P. Gupta, “Multimodal deep learning framework for media authenticity verification,” U.S. Patent 10 987 654, Aug. 25, 2020. (Standards style) [15] ISO, Information technology—Security techniques—Information security management systems—Requirements, ISO/IEC 27001:2022, 2022. [16] ISO and IEC, Information technology—Artificial intelligence—Concepts and terminology, ISO/IEC 22989:2022, 2022. (Handbook style) [17] R. C. Gonzalez and R. E. Woods, “Digital image processing fundamentals,” in Digital Image Processing, 4th ed., New York, NY, USA: Pearson, 2018, ch. 2, pp. 55–120. [18] D. Jurafsky and J. H. Martin, “Text classification and information extraction,” in Speech and Language Processing, 3rd ed., Upper Saddle River, NJ, USA: Prentice Hall, 2021, ch. 4, pp. 101–160. (Journal Online Sources style) [19] K. Shu, A. Sliva, S. Wang, J. Tang, and H. Liu, “Fake news detection on social media: A data mining perspective,” ACM SIGKDD Explorations Newsletter, vol. 19, no. 1, pp. 22–36, 2017.

© 2025 International Journal of Engineering and Techniques (IJET).

Digital Object Identifier (DOI)

IJET assigns a unique DOI to every accepted article via Zenodo for persistent linking and citation. Your article’s DOI: https://doi.org/{{doi}}

Open DOI About Zenodo DOI

Close