DETECTING DEEPFAKES USING HYBRID CNN-RNN MODEL

Abstract

We are living in the world of digital media and are connected to various types of digital media contents present in form of images and videos. Our lives are surrounded by digital contents and thus originality of content is very important. In the recent times, there is a huge emergence of deep learning-based tools that are used to create believable manipulated media known as Deepfakes. These are realistic fake media, that can cause threat to reputation, privacy and can even prove to be a serious threat to public security. These can even be used to create political distress, spread fake terrorism or for blackmailing anyone. As with growing technology, the tampered media getting generated are way more realistic that it can even bluff the human eyes. Hence, we need better deepfake detection algorithms for efficiently detect deepfakes. The proposed system that has been presented is based on a combination of CNN followed by RNN. The CNN model deployed here is SE-ResNeXt-101. The system proposed uses the CNN model SE-ResNeXt-101 model for extraction of feature vectors from the videos and further these feature vectors are utilized to train the RNN model which is LSTM model for classification of videos as Real or Deepfake. We evaluate our method on the dataset made by collecting huge number of videos from various distributed sources. We demonstrate how a simple architecture can be used to attain competitive results.