An effective approach for detecting deepfake videos using Long Short-Term Memory and ResNet

Deep learning algorithms are becoming more potent and producing human-synthesized, undifferentiated footage is a simple process thanks to advances in computing power. A method of synthesizing human images called deep fakes is built on neural network techniques like GAN. These technologies use deep learning algorithms to overlay target pictures onto the source films, producing realistic-looking deep-fake photos and videos. In this work, we provide a novel deep-learning approach that can reliably discriminate between actual and AI-generated fake videos. In this work, we test our method on a large number of balanced and mixed datasets created by mixing various publicly available datasets, such as Face-Forensic++, Deepfake detection, Celeb DF, and other publicly available datasets as images and videos, to emulate real-time scenarios and improve model performance with real-time data by using LSTM and ResNet.