Revealing and Classification of Deepfakes Video's Images using a Customize Convolution Neural Network Model

Abstract

Deepfake has been exploited in recent years despite its widespread usage in a variety of areas to create dangerous material such as fake movies, rumors, and false news by changing or substituting the face information of the sources and so poses enormous security concerns to society. Research on active detection & prevention technologies is critical as deepfake continues to evolve. Deepfake has been a blessing, but we've taken advantage of it by utilizing it to swap faces. Deepfake is a new subdomain of Artificial Intelligence (AI) technology in which one person's face is layered over another person's face, which is becoming more and more popular on social networking sites. Deepfake pictures and videos can now be created much more quickly and cheaply due to ML (Machine Learning), which is a primary component of deepfakes. Despite negative connotations attached to the term "deepfakes," technology is increasingly being used in commercial & individual contexts. New technical advancements have made it more difficult to distinguish between deepfakes and images that have been digitally manipulated. The rise of deepfake technologies has sparked a growing sense of unease. The primary goal of this project is to properly distinguish deepfake pictures from real images using deep learning techniques.In this study, we implemented a customized CNN algorithm to identify deepfake pictures from a video dataset and conducted a comparative analysis with two other methods to determine which way was superior. The Kaggle dataset was used to train & test our model. Convolutional neural networks (CNNs) have been used in this research to distinguish authentic & deepfake images by training three distinct CNN models. A customized CNN model, which includes several additional layers such as a dense layer, MaxPooling, as well as a dropout layer, has also been developed and implemented. This method follows the frames extraction, face feature extraction, data preprocessing, and classification phases in determining whether Real or Fake images in the video reflect the objectives. Accuracy, loss, and the area under the receiver operating characteristic (ROC) curve were used to characterize the data. Customized CNN outperformed all other models, achieving 91.4% accuracy, a reduced loss value of 0.342, as well as an AUC of 0.92. Besides, we obtained 85.2% testing accuracy from the CNN and 95.5% testing accuracy from the MLP-CNN model.