DUFormer: dual-channel image splicing detection based on anchor-shaped U-Net and stepwise transformer for power systems.

The safe operation of intelligent power systems relies on the authenticity and integrity of image data. However, splicing-based image tampering, a common form of image forgery, poses severe challenges to the security monitoring of power systems. Addressing the limitations of traditional image splicing detection techniques in power system applications, this paper introduces DUFormer, a dual-channel image splicing detection model that combines anchor-shaped U-Net and stepwise Transformer. The model explores image features through the stepwise Transformer and precisely locates small-sized tampered areas using the anchor-shaped U-Net, enhancing the recognition capability for tampering of various scales. Tests on the substation splicing forgery dataset (SSFD) dataset, which contains 1192 tampered images of power systems, show that DUFormer achieved a 32.76% improvement in intersection over union and a 29.77% improvement in F1 score, and a reduction in mean absolute error by 0.05 relative to the second-best performing model. Additionally, evaluations on multiple public datasets confirm that DUFormer surpasses existing detection technologies on various performance metrics, especially exhibiting outstanding performance at the level of detail. This paper also examines the model's robustness against JPEG compression operation to ensure its effectiveness in real-world applications. This research not only improves the pixel-level detection accuracy of power image splicing but also lays a solid foundation for the development of future security monitoring technologies for intelligent power systems. [ABSTRACT FROM AUTHOR]