SFNet: Fusion of Spatial and Frequency-Domain Features for Remote Sensing Image Forgery Detection

2025-06-25

AI Summary

To address the growing realism of generative-AI–forged remote sensing images (RSIs) and the poor generalizability of existing single-domain feature-based detection methods, this paper proposes SFNet—a dual-branch forgery detection framework jointly modeling spatial and frequency-domain features. SFNet constructs a frequency-branch via Fourier transform, synergistically fused with a spatial branch. A hybrid feature refinement module—integrating domain-specific feature mapping, multi-domain alignment, and CBAM-based enhancement—explicitly captures cross-domain complementary forensic cues. The framework is trained end-to-end, significantly improving robustness against diverse terrain/land-cover conditions and unseen generative models. Evaluated on three benchmark RSI datasets, SFNet achieves absolute accuracy gains of 4.0–15.18% over state-of-the-art methods and demonstrates superior cross-dataset generalization performance.

Technology Category

• Computer Vision: Remote Sensing / Geospatial AI
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Feature Construction/Reformulation

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

Abstract

The rapid advancement of generative artificial intelligence is producing fake remote sensing imagery (RSI) that is increasingly difficult to detect, potentially leading to erroneous intelligence, fake news, and even conspiracy theories. Existing forgery detection methods typically rely on single visual features to capture predefined artifacts, such as spatial-domain cues to detect forged objects like roads or buildings in RSI, or frequency-domain features to identify artifacts from up-sampling operations in adversarial generative networks (GANs). However, the nature of artifacts can significantly differ depending on geographic terrain, land cover types, or specific features within the RSI. Moreover, these complex artifacts evolve as generative models become more sophisticated. In short, over-reliance on a single visual cue makes existing forgery detectors struggle to generalize across diverse remote sensing data. This paper proposed a novel forgery detection framework called SFNet, designed to identify fake images in diverse remote sensing data by leveraging spatial and frequency domain features. Specifically, to obtain rich and comprehensive visual information, SFNet employs two independent feature extractors to capture spatial and frequency domain features from input RSIs. To fully utilize the complementary domain features, the domain feature mapping module and the hybrid domain feature refinement module(CBAM attention) of SFNet are designed to successively align and fuse the multi-domain features while suppressing redundant information. Experiments on three datasets show that SFNet achieves an accuracy improvement of 4%-15.18% over the state-of-the-art RS forgery detection methods and exhibits robust generalization capabilities. The code is available at https://github.com/GeoX-Lab/RSTI/tree/main/SFNet.

Problem

• Detect fake remote sensing images using spatial and frequency features
• Overcome limitations of single-feature methods in diverse terrains
• Improve generalization against evolving generative model artifacts

Innovation

• Fuses spatial and frequency-domain features
• Uses dual feature extractors for comprehensive analysis
• Aligns and refines features with CBAM attention