A Review on the Detection of Deep Fake and Propaganda Videos and Images-based Voice and Facial Manipulation using AI Techniques

The videos or images based on deep fake video is the creation of artificial intelligence models namely deep and machine learning techniques to superimpose, replace, combine and merge images as well as clips of videos thereby generating a video as fake, which seems trustworthy. Without involving this consent, the explicit content is generated is Deep-fake videos. Recently, Artificial Intelligence (AI) model is widely addressing the exciting task of autonomous control, object detection, image processing and enlarge data analysis. During the past years, the videos, images and audio are the form of deep fakes. A deepfake determination desires an evolution of technology. A person’s face or voice is swapped with another one during deepfakes thereby providing higher accurate videos. A deepfake determination desires an evolution of technology. To detect face or voice manipulation, novel AI models namely ML and DL to solve the deepfake detection challenges. The main objective of this research is to provide existing studies related to the detection of deepfake video or images based on different techniques, benchmark dataset, and discussion and future directions.