The distributed architecture and massive connectivity of 5G networks create significant security vulnerabilities that are challenging to address with centralized monitoring due to data privacy restrictions. Furthermore, the traffic data in such environments is characterized by extreme class imbalance, where critical but rare attacks are vastly outnumbered by benign traffic (with observed ratios exceeding 1:200). This paper introduces FedDTKG, a novel federated learning framework designed to provide robust, privacy-preserving intrusion detection under these challenging conditions. The framework features two key innovations: (1) a Temporal-Aware Self-Adaptive Graph Attention Network (TASA-GAT) that explicitly models the temporal dynamics and relational structure of network flows and (2) an Adaptive Synthetic Focal Loss (ASFL) that counters class imbalance by dynamically tuning its focus and incorporating a feature-level variance regularization term to improve minority class representation. We conduct a comprehensive evaluation on a non-IID distribution of 5G traffic data. In a centralized setting, FedDTKG achieves a state-of-the-art F1-macro score of 0.8756, significantly outperforming traditional ML and standard GNN baselines that fail to detect minority classes. In the federated setting, FedDTKG maintains a high F1-macro of 0.7546, whereas conventional GNNs fail completely, demonstrating our model’s resilience to statistical heterogeneity. The findings validate FedDTKG as an effective and practical solution for building collaborative, privacy-first security systems in real-world 5G edge networks.

In recent years, the exponential growth of internet usage worldwide has created a conducive environment for the expansion of malicious activities. Among these threats, malicious websites pose a significant risk to individual users and corporations. This paper presents a robust and efficient model for the detection of various types of malicious websites with high accuracy in the process. The proposed approach employs a two-step process. Firstly, a feature selection method based on the Firefly algorithm is utilized to identify the most relevant features. Subsequently, an optimized version of the XGBoost algorithm is applied to classify websites based on the selected features. Optimization of XGBoost's parameters is achieved through the Particle Swarm Optimization (PSO) algorithm to enhance its performance. To assess the efficacy of the introduced model, the model is evaluated against several benchmark classification algorithms using a dataset comprising over 36,000 websites. In binary classification, the introduced model surpasses other benchmark methods with a significant 98.42% classification accuracy and an F1 score of 0.984. For multiclass problem classification, it consistently achieves over 98% accuracy in each class. The test results highlight the proposed model's robust performance, characterized by exceptional classification accuracy and F1-measure rates. It demonstrates the capability to detect various types of malicious websites with high precision and minimal false error rates.

Internet of Things (IoT) as a new technological revolution has been proposed recently wherein the things are connected over the Internet. Because of the inherent characteristics of IoT for storage of data at untrusted and heterogeneous hosts, data replication across large geographic distances for efficient data management is unavoidable. The selection of appropriate replication things in the IoT, which reduces response time and cost is one of the most important issues of data management. Since this problem is an NP‐hard problem, classic approaches are not efficient to solve this issue, and evolutionary algorithm such as ant colony optimisation (ACO) and genetic algorithm (GA) seems to be very useful. This study offers a method based on a combination of ACO and a GA to solve this problem. In the proposed method, the ACO has been used to create diversity, and afterwards, the GA is performed to provide a full search over the search space. The obtained results have shown the better performance of the proposed method in comparison with ACO, the High‐QoS First‐Replication (HQFR), and the Response Time‐based Replica Management algorithms with regard to waiting time. In addition, the obtained results have revealed the better performance of the hybrid method in comparison with HQFR and the Dynamic Cost‐aware Re‐replication and Re‐balancing Strategy.