CrossDF: Improving Cross-Domain Deepfake Detection with Deep Information Decomposition
This addresses the threat of deepfakes to security and trust by enhancing detection robustness across different datasets, though it is an incremental improvement over prior methods.
The paper tackled the problem of cross-dataset deepfake detection, where existing methods degrade with unseen forgery techniques, and proposed a Deep Information Decomposition framework that improved performance by focusing on semantic features and achieving state-of-the-art results in experiments.
Deepfake technology poses a significant threat to security and social trust. Although existing detection methods have shown high performance in identifying forgeries within datasets that use the same deepfake techniques for both training and testing, they suffer from sharp performance degradation when faced with cross-dataset scenarios where unseen deepfake techniques are tested. To address this challenge, we propose a Deep Information Decomposition (DID) framework to enhance the performance of Cross-dataset Deepfake Detection (CrossDF). Unlike most existing deepfake detection methods, our framework prioritizes high-level semantic features over specific visual artifacts. Specifically, it adaptively decomposes facial features into deepfake-related and irrelevant information, only using the intrinsic deepfake-related information for real/fake discrimination. Moreover, it optimizes these two kinds of information to be independent with a de-correlation learning module, thereby enhancing the model's robustness against various irrelevant information changes and generalization ability to unseen forgery methods. Our extensive experimental evaluation and comparison with existing state-of-the-art detection methods validate the effectiveness and superiority of the DID framework on cross-dataset deepfake detection.