A Heterogeneous Feature Ensemble Learning based Deepfake Detection Method

Jixin Zhang, Ke Cheng, Giuliano Sovernigo, Xiaodong Lin

Abstract: The Deepfake technique can swap the face of a person with the face of another person in an image or a video which may cause a public security problem. Recently, researchers have focused on detecting deepfake images by deep learning. However some recent works have observed that detectors trained on images produced by one deepfake model perform poorly when tested on others. In this paper we propose to detect deepfake images through heterogeneous feature ensemble learning. We first extract gray gradient features, spectrum features and texture features from real and fake face images, then integrate them into an ensemble feature vector through a flatten process, and finally adopt a back-propagation neural network to train a deepfake detector with the feature vector. Experimental results show that our approach achieves better detection accuracy compared with several state-of-the-art deepfake detectors.