The evolution of multimedia manipulation techniques has led to the progression of DeepFake, a generative deep learning system that specializes in creating remarkably realistic facial characteristics. While this technology is revolutionizing applications for improving visual effects in TV channels, video games, and movies, it also raises worries because of its possible misuse, particularly in illegal actions like disseminating false information by impersonating public individuals. This survey explores the realm of DeepFake identification and highlights the growing interest in research employing deep neural networks (DNNs) to recognize and categorize these misleading media productions. Here, we present a thorough analysis of the Cutting-edge DeepFake generation techniques, grouping them into five key categories and summarizing face picture and video detection strategies based on methodology, performance metrics, types of detection, and outcomes. DeepFake models are usually tested through experiments after being trained on certain datasets. The survey investigates advancements in this field and identifies changing patterns in DeepFake datasets. The abstract also explores the task of developing a universal DeepFake detection model and discusses the related difficulties in both development and detection. The objective is to expedite the modulation of deep learning for enhancing techniques in detecting DeepFakes in both facial images and videos.