HFMF: Hierarchical Fusion Meets Multi-Stream Models for Deepfake Detection

2025-01-10

AI Summary

To address the growing challenge of distinguishing authentic from AI-generated content—particularly deepfakes produced by diffusion models and GANs—this paper proposes a two-stage deepfake detection framework. In the first stage, a hierarchical cross-modal feature fusion mechanism jointly leverages Vision Transformers and CNNs to collaboratively model local textures, global structures, and multi-scale discriminative representations. The second stage introduces object-level semantic attention and fine-tuned CNN features, integrated via an ensemble neural network for robust classification. Our key contributions include the first hierarchical cross-modal fusion architecture and a multi-stream feature collaboration design. Evaluated on multiple benchmark datasets, the method achieves state-of-the-art performance, significantly improving detection accuracy, calibration, and generalization to unseen generative models, while preserving model interpretability and cross-platform deployability.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Deep Generative Models & Autoencoders
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems

Abstract

The rapid progress in deep generative models has led to the creation of incredibly realistic synthetic images that are becoming increasingly difficult to distinguish from real-world data. The widespread use of Variational Models, Diffusion Models, and Generative Adversarial Networks has made it easier to generate convincing fake images and videos, which poses significant challenges for detecting and mitigating the spread of misinformation. As a result, developing effective methods for detecting AI-generated fakes has become a pressing concern. In our research, we propose HFMF, a comprehensive two-stage deepfake detection framework that leverages both hierarchical cross-modal feature fusion and multi-stream feature extraction to enhance detection performance against imagery produced by state-of-the-art generative AI models. The first component of our approach integrates vision Transformers and convolutional nets through a hierarchical feature fusion mechanism. The second component of our framework combines object-level information and a fine-tuned convolutional net model. We then fuse the outputs from both components via an ensemble deep neural net, enabling robust classification performances. We demonstrate that our architecture achieves superior performance across diverse dataset benchmarks while maintaining calibration and interoperability.

Problem

• Deep Learning
• Forgery Detection
• Misinformation Prevention

Innovation

• Hierarchical Fusion
• Multi-stream Model
• DeepFake Detection