Foggy ship detection frequently suffers from image degradation, blurred object contours and a high missed detection rate. Moreover, most existing maritime datasets lack adequate real fog samples. To solve the above problems, in this paper, the Fog-SMD is constructed on the basis of atmospheric scattering principles and fractal theory in combination with a diffusion model to enrich samples covering various fog scenarios. On this basis, we develop an improved SF-YOLO model that takes YOLOv12 as the basic framework. By embedding the shallow–deep adaptive feature fusion module, scattering-guided refinement module and spatial-frequency dual feature attention module, the model can effectively alleviate feature loss resulting from image degradation in foggy environments. Weighted-EIoU loss is introduced to optimize the bounding box regression and reduce the localization deviation of slender ship targets. The experimental results show that SF-YOLO achieves mAP@50 and mAP@50:95 values of 79.3% and 61.6%, respectively, and outperforms mainstream detection algorithms; compared with YOLOv12n, it improves mAP@50:95 from 59.6% to 61.6%, with only a slight increase in parameters from 2.5 M to 2.8 M, providing a new solution for the practical deployment of detection systems and all-weather maritime monitoring in low-visibility foggy scenarios.