Investigating some methods for detecting Deepfake in Deep learning

Abstract

Deep Learning can be considered a subfield of Machine Learning– where computers learn and improve themselves through algorithms. It has been successfully applied to solve complex problems ranging from big data analytics to computer vision and human-level control. However, Deep Learning advances have also been used to create software that can pose threats to privacy, democracy, and national security. One of the new applications that has appeared recently is “Deepfakes”. Deepfake algorithms can create fake images and videos that humans cannot distinguish from real images or videos. Therefore, being able to detect and evaluate the correctness of images or videos is a current problem.