Fighting Against Deepfake: Patch&Pair Convolutional Neural Networks (PPCNN)
Xurong Li, Kun Yu, Shouling Ji, Yan Wang, Chunming Wu, Hui Xue
Abstract
In this paper, we propose a novel Patch&Pair Convolutional Neural Networks (PPCNN) to distinguish Deepfake videos or images from real ones. Through the comprehensive evaluations on public datasets, we demonstrate that our model performs better than existing detection methods and show better generalization.
Topics & Concepts
Convolutional neural networkGeneralizationComputer scienceArtificial intelligenceMachine learningMathematicsMathematical analysisDigital Media Forensic DetectionGenerative Adversarial Networks and Image SynthesisAnomaly Detection Techniques and Applications