Deepfake Detection Using Deep Learning

Abstract

Four billion images are uploaded to the internet every day, according to polls. With the widespread use of digital photography, new methods for modifying image content employing tools, apps, and editing software like Adobe's have emerged. Deepfake techniques were used to create a fake movie and photos, which has raised significant public concern. The majority of face-manipulation techniques used in videos today, such as Faceswap and Deepfake, have been created successfully. It has both benefits and drawbacks. On the one hand, it broadens the application to new fields (such as visual arts, visual studies, filmmaking, etc.), but on the other, it also fosters harmful users. Consequently, we can determine whether the video is real or not by applying Deep Learning algorithms. We're going to create a system that can identify this dangerous data in order to recognise it.