DA-HFNet: Progressive Fine-Grained Forgery Image Detection and Localization Based on Dual Attention

TL;DR

This paper introduces DA-HFNet, a hierarchical dual-attention network that improves the detection and localization of AI-generated forged images by capturing artifacts at multiple scales and leveraging multi-modal features.

Contribution

The paper presents a novel hierarchical progressive network with dual-attention for fine-grained forgery detection and localization, along with a new forged image dataset.

Findings

Significant performance improvements over state-of-the-art methods

Effective multi-scale artifact capture and feature fusion

Enhanced detection accuracy using noise fingerprint extraction

Abstract

The increasing difficulty in accurately detecting forged images generated by AIGC(Artificial Intelligence Generative Content) poses many risks, necessitating the development of effective methods to identify and further locate forged areas. In this paper, to facilitate research efforts, we construct a DA-HFNet forged image dataset guided by text or image-assisted GAN and Diffusion model. Our goal is to utilize a hierarchical progressive network to capture forged artifacts at different scales for detection and localization. Specifically, it relies on a dual-attention mechanism to adaptively fuse multi-modal image features in depth, followed by a multi-branch interaction network to thoroughly interact image features at different scales and improve detector performance by leveraging dependencies between layers. Additionally, we extract more sensitive noise fingerprints to obtain more prominent forged artifact features in the forged areas. Extensive experiments validate the effectiveness of our approach, demonstrating significant performance improvements compared to state-of-the-art methods for forged image detection and localization.The code and dataset will be released in the future.