Deepfake Media Detection Framework Using Machine Learning with Multimodal Feature Extraction for Real and Synthetic Content

The emergence of contemporary deepfakes has at tracted significant attention in machine learning research, as artificial intelligence (AI) generated synthetic media increases the incidence of misinterpretation and is difficult to distinguish from genuine content.Techniques for creating and manipulating multimedia information have progressed to the point where they can now ensure a high degree of realism. DeepFake is a generative deep learning algorithm that creates or modifies face features in a superrealistic form, making it difficult to distinguish between real and fake features. This technology has greatly advanced, promoting a wide range of applications in cinema, such as improving visual effects in movies, as well as various criminal activities, such as misinformation generation by mimicking famous people. To identify and classify DeepFakes, research in DeepFake detection using Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) has attracted increased interest. Essentially, DeepFake is regenerated media obtained by injecting or replacing some information within CNN and RNN models. This paper summarizes the DeepFake detection methods for face images and videos based on their results, performance, methodology used, and detection type. The challenges in generating a generalized DeepFake detection model are also analyzed.