A Deep Approach to Deep Fake Detection
DOI:
https://doi.org/10.32628/IJSRSET2411274Keywords:
Deepfake Video Detection, Generative Adversarial Network, Convolutional Neural Network, Recurrent Neural NetworkAbstract
In recent months, the proliferation of free deep learning-based software tools has facilitated the creation of credible face exchanges in videos, resulting in what are known as "DeepFake" (DF) videos. While manipulations of digital videos have been demonstrated for several decades through the use of visual effects, recent advances in deep learning have significantly increased the realism of fake content and the accessibility with which it can be created. These AI-synthesized media, popularly referred to as DF, pose a significant challenge for detection. Detecting DF is a major challenge due to the complexity of training algorithms to spot them. In this work, we propose a detection approach using Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs). Our system leverages a CNN to extract features at the frame level, which are then used to train an RNN. The RNN learns to classify whether a video has been manipulated, detecting temporal inconsistencies between frames introduced by DF creation tools. We evaluate our approach against a large set of fake videos collected from standard datasets and demonstrate competitive results using a simple architecture.
Downloads
References
Chen, Y., Liu, X., & Yuen, P. C. (2022). "Deepfake Detection Using Adversarial Training Techniques." IEEE Transactions on Information Forensics and Security, 17(5), 977-990.
Li, H., Li, Y., & Tan, Y. (2023). "Multimodal Deepfake Detection via Attention Mechanism." Pattern Recognition Letters, 150, 100-108.
Zhang, L., Wu, Q., & Zhang, S. (2022). "Detecting Deepfake Videos Using Spatiotemporal Features and Long Short-TermMemory Networks." Multimedia Tools and Applications, 81(12), 20467-20482. DOI: https://doi.org/10.1007/s11042-021-11733-y
Wang, J., Liu, S., & Yang, X. (2023). "Deepfake Detection Based on Capsule Networks and Temporal-Spatial Attention Mechanism." IEEE Access, 11, 11280-11291.
Park, S., Kim, J., & Lee, S. (2022). "Robust Deepfake Detection Using Ensemble Learning with Feature Fusion." Expert Systems with Applications, 195, 114219.
Zhou, W., Xu, J., & Wu, X. (2023). "Deepfake Detection with Graph Convolutional Networks on Dynamic Graphs." Neurocomputing, 475, 1098-1107.
Huang, Q., Wang, Y., & Zhang, L. (2022). "Forgery Detection in Deepfake Videos Using GAN-Based Methods." Information Sciences, 601, 60-72.
Kim, H., Cho, S., & Lee, H. (2023). "Deepfake Detection Based on Facial Geometry and Texture Analysis." Journal of Visual Communication and Image Representation, 99, 103174.
Chen, Z., Liu, Y., & Zhang, T. (2022). "Deepfake Detection Using Temporal Coherence Analysis and Convolutional Neural Networks." Signal Processing: Image Communication, 105, 116420.
Jiang, H., Li, X., & Xu, Z. (2023). "Deepfake Detection via Temporal Consistency Analysis and Two-Stream Convolutional Networks." IEEE Transactions on Circuits and Systems for Video Technology, 33(5), 1815-1826.
Guo, Q., Li, H., & Ma, Z. (2022). "Deepfake Detection Based on Two-Stream Spatio Temporal Networks and Domain Knowledge." Pattern Recognition, 127, 108180.
Wu, Y., Li, Z., & Liu, Y. (2023). "A Hybrid Approach for Deepfake Detection Using Fusion of Frequency Domain and Temporal Information." Multimedia Tools and Applications, 82(1), 757-775
Zhang, M., Zhang, Y., & Wang, Z. (2022). "Detecting Deepfake Videos Using Motion Magnification and Convolutional Neural Networks." IEEE Access, 10, 120571-120581. DOI: https://doi.org/10.1109/ACCESS.2022.3173444
Wang, X., Wang, L., & Jiang, J. (2023). "Deepfake Detection Based on Face Warping Analysis and Convolutional Neural Networks." Multimedia Tools and Applications, 82(5), 6929-6945.
Li, Y., Zhang, Y., & Zheng, Y. (2022). "An Ensemble Approach for Deepfake Detection Combining Handcrafted Features and Deep Learning." Information Fusion, 85, 204-214.
Yang, J., Guo, X., & Li, H. (2023). "Deepfake Detection Using Visual Attention Mechanism and Temporal Consistency Analysis." Pattern Recognition Letters, 154, 39-46.
Liu, Q., Wu, X., & Zhang, Y. (2022). "Deepfake Detection Using Phase Spectrum Analysis and Convolutional Neural Networks." Signal Processing: Image Communication, 107, 116450.
Hu, Z., Wang, W., & Wu, J. (2023). "Robust Deepfake Detection Based on Capsule Networks and Adversarial Examples." IEEE Transactions on Multimedia, 25(8), 3628-3641. DOI: https://doi.org/10.1109/TMM.2022.3163459
Kim, S., Jung, J., & Kim, J. (2022). "Deepfake Detection Using Two-Stream Networks and Motion Features." Expert Systems with Applications, 203, 115940.
Liu, J., Zhang, Z., & Li, W. (2023). "Detecting Deepfake Videos with Attention Mechanism and Graph Convolutional Networks." Neurocomputing, 486, 111-121.
Downloads
Published
Issue
Section
License
Copyright (c) 2024 International Journal of Scientific Research in Science, Engineering and Technology
This work is licensed under a Creative Commons Attribution 4.0 International License.
How to Cite
