ORIGINAL RESEARCH article
Front. Big Data
Sec. Cybersecurity and Privacy
Volume 8 - 2025 | doi: 10.3389/fdata.2025.1669488
This article is part of the Research TopicNew Trends in AI-Generated Media and SecurityView all 4 articles
CrossDF: Improving Cross-Domain Deepfake Detection with Deep Information Decomposition
Provisionally accepted
- 1Chengdu University of Information Technology, Chengdu, China
- 2University at Buffalo, Buffalo, United States
- 3Purdue University, West Lafayette, United States
- 4Microsoft Research Asia, Beijing, China
- 5University at Albany - Downtown Campus, Albany, United States
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
ABSTRACT Deepfake technology represents a serious risk to safety and public confidence. While current detection approaches perform well in identifying manipulations within datasets that utilize identical deepfake methods for both training and validation, they experience notable declines in accuracy when applied to cross-dataset situations, where unfamiliar deepfake techniques are encountered during testing. To tackle this issue, we propose a Deep Information Decomposition (DID) framework to improve Cross-dataset Deepfake Detection (CrossDF). Distinct from most existing deepfake detection approaches, our framework emphasizes high-level semantic attributes instead of focusing on particular visual anomalies. More specifically, it intrinsically decomposes facial representations into deepfake-relevant and unrelated components, leveraging only the deepfake-relevant features for classification between genuine and fabricated images. Furthermore, we introduce an adversarial mutual information minimization strategy that enhances the separability between these two types of information through decorrelation learning. This significantly improves the model's robustness to irrelevant variations and strengthens its generalization capability to previously unseen manipulation techniques. Extensive experiments demonstrate the effectiveness and superiority of our proposed DID framework for cross-dataset deepfake detection. It achieves an AUC of 0.779 in cross-dataset evaluation from FF++ to CDF2 and improves the state-of-the-art AUC significantly from 0.669 to 0.802 on the diffusion-based Text-to-Image dataset.
Keywords: DeepFake Detection, deep information decomposition, Model Generalization, decorrelation learning, Cross-dataset
Received: 25 Jul 2025; Accepted: 18 Sep 2025.
Copyright: © 2025 Yang, Guo, Hu, Zhu, Fu, Lyu, Wu and Wang. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence: Shanmin Yang, yangsm@cuit.edu.cn
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.