Open Access Open Access  Restricted Access Subscription Access

Deepfake Video Detection Framework Using Multimodal Feature Extraction and Temporal Modeling

Abel Daison, Albin Jijo, Edwin Jose, Gokul S, Dr. Asha S

Abstract


The increase in threats caused by the realistic deepfake videos have made the necessity for detection mech- anisms to control the misuse. The project aims to create a deepfake detection framework using feature extraction and sequence modeling techniques aiming at an improved accuracy in detection. InceptionV3 is used as feature extractor where the system process video frames to find the spatial details. The two layer Gated Recurrent Unit (GRU) is used to model temporal dependencies within video sequences. The proposed framework pre-processes each video to standardize frame dimensions and a masking mechanism is applied to handle variable sequence lengths, therefore optimizing the performance across diverse video samples. Training is done using a dataset consisting of both ‘Real’ and ‘Fake’ videos allowing the system to achieve accuracy. Evaluations state that the model captures both spatial and temporal anomalies characteristic of deepfake videos, making it appropriate for real-world applications. The proposed system is offering a scalable and a very efficient solution to solve the growing challenges of deepfake detection.

Full Text:

PDF

References


M. Westerlund, “The emergence of deepfake technology: A review,”

Technology innovation management review, vol. 9, no. 11, 2019.

A. Karpathy, G. Toderici, S. Shetty, T. Leung, R. Sukthankar, and

L. Fei-Fei, “Large-scale video classification with convolutional neural networks,” in Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, pp. 1725–1732, 2014.

P. Yu, Z. Xia, J. Fei, and Y. Lu, “A survey on deepfake video detection,”

Iet Biometrics, vol. 10, no. 6, pp. 607–624, 2021.

N. Bansal, T. Aljrees, D. P. Yadav, K. U. Singh, A. Kumar, G. K. Verma, and T. Singh, “Real-time advanced computational intelligence for deep fake video detection,” Applied Sciences, vol. 13, no. 5, p. 3095, 2023.

J. Thies, M. Zollhofer, M. Stamminger, C. Theobalt, and M. Nießner, “Face2face: Real-time face capture and reenactment of rgb videos,” in Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 2387–2395, 2016.

R. Dey and F. M. Salem, “Gate-variants of gated recurrent unit (gru) neural networks,” in 2017 IEEE 60th international midwest symposium on circuits and systems (MWSCAS), pp. 1597–1600, IEEE, 2017.

A. E. Tio, “Face shape classification using inception v3,” arXiv preprint arXiv:1911.07916, 2019.

S. Suratkar and F. Kazi, “Deep fake video detection using transfer learning approach,” Arabian Journal for Science and Engineering, vol. 48, no. 8, pp. 9727–9737, 2023.

M. H. Malik, H. Ghous, S. Qadri, S. A. Nawaz, and A. Anwar, “Frequency-based deep-fake video detection using deep learning meth- ods,” Journal of Computing & Biomedical Informatics, vol. 4, no. 02,

pp. 41–48, 2023.

G. Van Houdt, C. Mosquera, and G. Na´poles, “A review on the long short-term memory model,” Artificial Intelligence Review, vol. 53, no. 8,

pp. 5929–5955, 2020.


Refbacks

  • There are currently no refbacks.