An Effective Approach for Deepfake Video Detection using Binarized Neural Network

The rise of DeepFake technologies, especially in audio and video, poses significant threats to information integrity, security, and privacy. Artificially driven Artificial Intelligence (AI) methods and their advancement make it difficult to trace synthetic media through deepfakes that closely approximate real speech, facial expressions, and body movements. Consequently, traditional methods of detecting these are losing the race because they cannot compete with the newly invented methods that are more advanced in comparison. This paper proposes a lightweight and scalable approach to deepfake video detection using Binarized Neural Networks (BNNs). We integrate BNNs with Convolutional Neural Networks (CNNs) and Multi-task Cascaded Convolutional Networks (MTCNN) to boost feature extraction and analysis while making sure that this is done at a computational efficiency, especially to be deployed in resource-constrained systems such as mobile and embedded devices. The binarization of network weights and activations naturally deals with the trade-off regarding detection accuracy and computational cost. Our approach introduces a practical solution for real-time deepfake detection, thus advancing toward more secure and trusted digital environments. Our proposed model has achieved an accuracy of 80%.