Developing an intelligent model for accurate detection of cyber threats in smart logistics networks

Supply Chain Management in the logistics sector involves coordinating processes, resources, and information to ensure the smooth flow of goods and services from suppliers to end customers. However, smart logistics networks are increasingly exposed to cyber threats such as data breaches, ransomware, and unauthorized access to IoT devices, which can disrupt operations and compromise sensitive data. In this study, the BoT-IoT dataset from the Kaggle platform is used. Data preprocessing is performed using Z-score normalization to standardize the data. Principal Component Analysis (PCA) is applied to reduce dimensionality, while Recursive Feature Elimination (RFE) is used to select the most relevant features. For classification, a novel Optimized Grey Recurrence Neuro Net Classifier is developed, which combines the global search capability of the Grey Wolf Optimizer (GWO) with Recurrent Neural Networks (RNNs) to improve detection performance. The model is implemented using Python tools and libraries. Experimental results show that the proposed method outperforms existing approaches, achieving 99.99% accuracy, 99.99% precision, 100% recall, and a 99.99% F1 score, demonstrating its high effectiveness and efficiency.