Unveiling Deepfakes: A Frequency-Aware Triple Branch Network for Deepfake Detection

2026-04-19

AI Summary

Existing deepfake detection methods suffer from limited generalization due to their confinement to a single frequency domain or the presence of redundant features. To address this, this work proposes a frequency-aware triple-branch network that jointly learns spatial and frequency-domain features from the original image and its multi-frequency reconstructed representations. A mutual information–based feature disentanglement and fusion loss is introduced to enhance both feature diversity and task relevance. The proposed method achieves state-of-the-art performance across six large-scale benchmark datasets, demonstrating significantly improved robustness and generalization against diverse forgery patterns.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Multimodal Learning
• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

Advanced deepfake technologies are blurring the lines between real and fake, presenting both revolutionary opportunities and alarming threats. While it unlocks novel applications in fields like entertainment and education, its malicious use has sparked urgent ethical and societal concerns ranging from identity theft to the dissemination of misinformation. To tackle these challenges, feature analysis using frequency features has emergedas a promising direction for deepfake detection. However, oneaspect that has been overlooked so far is that existing methodstend to concentrate on one or a few specific frequency domains,which risks overfitting to particular artifacts and significantlyundermines their robustness when facing diverse forgery patterns. Another underexplored aspect we observe is that different features often attend to the same forged region, resulting in redundant feature representations and limiting the diversity of the extracted clues. This may undermine the ability of a model to capture complementary information across different facets, thereby compromising its generalization capability to diverse manipulations. In this paper, we seek to tackle these challenges from two aspects: (1) we propose a triple-branch network that jointly captures spatial and frequency features by learning from both original image and image reconstructed by different frequency channels, and (2) we mathematically derive feature decoupling and fusion losses grounded in the mutual information theory, which enhances the model to focus on task-relevant features across the original image and the image reconstructed by different frequency channels. Extensive experiments on six large-scale benchmark datasets demonstrate that our method consistently achieves state-of-the-art performance. Our code is released at https://github.com/injooker/Unveiling Deepfake.

Problem

• deepfake detection
• frequency domain
• feature redundancy
• generalization capability
• forgery patterns

Innovation

• frequency-aware
• triple-branch network
• feature decoupling
• mutual information
• deepfake detection