Multi-layer Face Forgery Detection Framework Based on Image Decomposition and Attention Mechanism

• 1、Cyberspace Security School, Beijing University of Posts and Telecommunications, Beijing

Abstract：The rapid development of deepfake technology and the complexity and diversity of deepfake methods have raised higher requirements for deepfake detection. Meanwhile, how to improve the generalization ability of detection algorithms under the current dataset is one of the main difficulties in deepfake detection. Aiming at this problem, we proposes a multi-layer deepfake detection framework based on image decomposition and inter-layer spatial attention transfer. Compared with directly using pre-trained models, we attempts to extract fake features by designing a network model that can extract differences between real and fake faces. We adopts the idea of decomposing the original input and extracting features layer by layer, using Laplacian pyramid for image decomposition to separate the differences and commonalities between real and fake samples as much as possible. The inter-layer spatial attention transfer module is proposed to enhance the model\'s ability to extract differences, thereby strengthening the generalization ability of the detection model. The experimental results show that the model proposed in this study performs well within the dataset and has strong performance in cross-dataset testing.

Keywords： face forgery detection image forensics attention mechanism