Video Morphing Attack Detection using Convolutional Neural Networks on Deep Fake Algorithm

A method called deepfake produces fake video and films with artificial or substituted faces. Deepfakes are turning into a worrying societal phenomenon because they may be used maliciously to spread harmful information, fabricate electronic convincing proof, make fake political news, and even participate in online harassment and fraud. These masks make it harder to distinguish facial features, making it more difficult to detect fake video. To detect the fake morphed video, we are using the deepfake algorithm to detect the morphed face in the video. Deepfake technology is not using to create the morphed video and also it is used to detect the video by using the CNN.As a result, more sophisticated deepfake detection technology is required. Because the field does not yet have the necessary dataset for detection-model training, the research generates a real or fake video dataset with face masks The study attempts to improve accuracy by improving CNN topologies, detecting important visual signals, and comparing model performance against various morphing strategies. Real-world application of the effect of dataset size and diversity on training is investigated. By protecting multimedia material against changing digital tampering, this research helps combat the threat posed by deepfake technology.