This paper addresses the critical challenge of secure computing in the context of deep learning, focusing on the pressing need for effective data privacy protection during transmission and storage, particularly in sensitive fields such as finance and healthcare. To tackle this issue, we propose a novel deep learning model that integrates a hash tree structure with a skip attention mechanism. The hash tree is employed to ensure data integrity and security, enabling the rapid verification of data changes, while the skip attention mechanism enhances computational efficiency by allowing the model to selectively focus on important features, thus minimizing unnecessary processing. The primary objective of our research is to develop a secure computing model that not only safeguards data privacy but also optimizes feature extraction capabilities. Our experimental results on the CIFAR-10 dataset demonstrate significant improvements over traditional models, achieving a precision of 0.94, a recall of 0.89, an accuracy of 0.92, and an F1-score of 0.91, notably outperforming standard self-attention and CBAM. Additionally, the visualization of results confirms that our approach effectively balances efficient feature extraction with robust data privacy protection. This research contributes a new framework for secure computing, addressing both the security and efficiency concerns prevalent in current methodologies.

This paper proposes a disease detection model based on the maxmin-diffusion mechanism, aimed at improving the accuracy and robustness of disease detection tasks in the agricultural field. With the development of smart agriculture, automated disease detection has become one of the key tasks driving agricultural modernization. Traditional disease detection models often suffer from significant accuracy loss and robustness issues when dealing with complex disease types and dynamically changing time-series data. To address these problems, this paper introduces the maxmin-diffusion mechanism, which dynamically adjusts attention weights to enhance the model’s focus on key disease regions while suppressing interference from irrelevant areas, significantly improving the segmentation accuracy of disease regions. Through a series of experiments, the proposed model demonstrates outstanding performance across various disease detection tasks. For bacterial spot disease detection, the model achieves a precision of 0.98, recall of 0.95, accuracy of 0.96, and mIoU of 0.96, indicating that it can efficiently and accurately identify disease regions even in complex backgrounds. Compared to traditional self-attention and CBAM mechanisms, the maxmin-diffusion mechanism shows significant advantages in fine-grained feature extraction and time-series data processing, particularly in the recognition of dynamically changing disease regions, where it exhibits higher detection accuracy and robustness. Furthermore, the model underwent lightweight optimization, enabling the proposed disease detection model to not only achieve high-precision detection but also run efficiently on resource-constrained mobile devices. This provides strong technical support for the application of smart agriculture.