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

TL;DR

HFMF introduces a two-stage deepfake detection framework that combines hierarchical cross-modal feature fusion and multi-stream analysis, significantly improving detection accuracy against advanced AI-generated fake images and videos.

Contribution

The paper presents a novel two-stage deepfake detection method integrating hierarchical feature fusion and multi-stream analysis, outperforming existing approaches on multiple benchmarks.

Findings

Achieves superior detection accuracy across diverse datasets.

Maintains calibration and interoperability in detection results.

Effectively leverages vision Transformers and convolutional nets.

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.