CrossDF: Improving Cross-Domain Deepfake Detection with Deep Information Decomposition

TL;DR

This paper introduces CrossDF, a deepfake detection framework that decomposes facial features into deepfake-related and irrelevant information to improve cross-dataset detection robustness and generalization.

Contribution

The paper proposes a novel Deep Information Decomposition framework that enhances cross-dataset deepfake detection by focusing on semantic features and enforcing independence between information types.

Findings

Outperforms existing methods in cross-dataset scenarios

Enhances robustness against unseen deepfake techniques

Improves generalization by focusing on semantic features

Abstract

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.