IRO Journals
Journal of Ubiquitous Computing and Communication Technologies

Multimodal Deepfake Detection using Meso4 CNN for Spatial Image Analysis and LRCN for Temporal Video Analysis

Open Access
Published: 13 October, 2026
Pages: 313-325
  • Mahalakshmi K. , Mahalakshmi K.
    Student, Department of Artificial Intelligence and Data Science, Prathyusha Engineering College, Tamil Nadu, India
    Student, Department of Artificial Intelligence and Data Science, Prathyusha Engineering College, Tamil Nadu, India
  • Lavanya A. , Lavanya A.
    Student, Department of Artificial Intelligence and Data Science, Prathyusha Engineering College, Tamil Nadu, India
    Student, Department of Artificial Intelligence and Data Science, Prathyusha Engineering College, Tamil Nadu, India
  • Kiruthika R. , Kiruthika R.
    Student, Department of Artificial Intelligence and Data Science, Prathyusha Engineering College, Tamil Nadu, India
    Student, Department of Artificial Intelligence and Data Science, Prathyusha Engineering College, Tamil Nadu, India
  • Kannamma R. Kannamma R.
    Assistant Professor, Department of Artificial Intelligence and Data Science, Prathyusha Engineering College, Tamil Nadu, India
    Assistant Professor, Department of Artificial Intelligence and Data Science, Prathyusha Engineering College, Tamil Nadu, India
view PDF
view PDF

How to Cite

K., Mahalakshmi, Lavanya A., Kiruthika R., and Kannamma R. 2026. “Multimodal Deepfake Detection Using Meso4 CNN for Spatial Image Analysis and LRCN for Temporal Video Analysis”. Journal of Ubiquitous Computing and Communication Technologies 8 (4): 313-25. https://doi.org/10.36548/jucct.2026.4.001.
ACM ACS APA ABNT Chicago Harvard IEEE MLA Turabian Vancouver AMA

Download Citation

Endnote/Zotero/Mendeley (RIS) BibTeX

Keywords

Deepfake Forensics
MesoNet Convolutional Neural Network
Long Short-Term Convolutional Recurrent Network
Facial Manipulation Detection
Mesoscopic Feature Learning
Spatiotemporal Analysis
Sequential Video Frame Analysis

Abstract

Generative artificial intelligence technology has resulted in the creation of deepfakes, highly realistic forged images and videos, posing major automated media authentication challenges. This research proposes a multimodal approach for deepfake recognition based on Meso4 CNN and Long Short-Term Convolutional Recurrent Network (LRCN). The proposed approach includes input validation, resizing, normalization, and data augmentation followed by feature extraction and real-fake classification for each modality. While Meso4 CNN is responsible for extracting mesoscopic facial features from images, LRCN analyzes the temporal inconsistencies in a sequence of video frames. The proposed system was tested on the FaceForensics++ dataset and analysed the performance metrics such as accuracy, precision, and recall. The proposed system has resulted in 94.1% accuracy, 93.5% precision, and 94.6% recall.

References

  1. Guarnera, Luca, Oliver Giudice, and Sebastiano Battiato. "Deepfake detection by analyzing convolutional traces." In 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), IEEE, 2020, 2841-2850.
  2. Li, Meng, Beibei Liu, Yongjian Hu, Liepiao Zhang, and Shiqi Wang. "Deepfake Detection using Robust Spatial and Temporal Features from Facial Landmarks." In 2021 IEEE International Workshop on Biometrics and Forensics (IWBF), IEEE, 2021, 1-6.
  3. Rana, Md Shohel, Mohammad Nur Nobi, Beddhu Murali, and Andrew H. Sung. "Deepfake Detection: A Systematic Literature Review." IEEE Access, 2022, vol. 10: 25494-25513.
  4. Patel, Yogesh, Sudeep Tanwar, Rajesh Gupta, Pronaya Bhattacharya, Innocent Ewean Davidson, Royi Nyameko, Srinivas Aluvala, and Vrince Vimal. "Deepfake Generation and Detection: Case Study and Challenges." IEEE Access, 2023, vol. 11: 143296-143323.
  5. Edwards, Peter, Jean-Christophe Nebel, Darrel Greenhill, and Xing Liang. "A Review of Deepfake Techniques: Architecture, Detection, and Datasets." IEEE Access, 2024, vol. 12 154718-154742.
  6. Afchar, Darius, Vincent Nozick, Junichi Yamagishi, and Isao Echizen. "Mesonet: A Compact Facial video Forgery Detection Network." In 2018 IEEE international workshop on information forensics and security (WIFS), IEEE, 2018, 1-7.
  7. Nguyen, Huy H., Junichi Yamagishi, and Isao Echizen. "Capsule-Forensics: Using Capsule Networks to Detect Forged Images and Videos." In ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE, 2019, 2307-2311.
  8. Tolosana, Ruben, Ruben Vera-Rodriguez, Julian Fierrez, Aythami Morales, and Javier Ortega-Garcia. "Deepfakes And Beyond: A Survey of Face Manipulation and Fake Detection." Information Fusion, 2020, vol. 64: 131-148.
  9. Chen, Beijing, Tianmu Li, and Weiping Ding. "Detecting Deepfake videos Based on Spatiotemporal Attention and Convolutional LSTM." Information Sciences, 2022, vol. 601: 58-70.
  10. Tan, Chuangchuang, Yao Zhao, Shikui Wei, Guanghua Gu, Ping Liu, and Yunchao Wei. "Frequency-Aware Deepfake Detection: Improving Generalizability Through Frequency Space Domain Learning." In Proceedings of the AAAI Conference on Artificial Intelligence, 2024, vol. 38, no. 5: 5052-5060.
  11. Rossler, Andreas, Davide Cozzolino, Luisa Verdoliva, Christian Riess, Justus Thies, and Matthias Nießner. "Faceforensics++: Learning to Detect Manipulated Facial Images." In Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019, 1-11. https://github.com/ondyari/FaceForensics