Enhancing Security and Trust Management in IoT-Driven Edge Computing Environment using Ensemble Learning Techniques

The rapid expansion of Internet of Things (IoT) devices in edge and fog computing environments poses significant cybersecurity challenges, especially in addressing malware threats. The proposed method uses a dynamic trust assessment algorithm, which continuously monitors and evaluates the behavior of IoT devices to obtain a trust score. These scores are used to modify the sensitivity of the malware detection system and check if devices are among the few that do not believe are put to a severe test. Furthermore, the ensemble learning model uses XGBoost and AdaBoost to detect malware with high accuracy and low false positive rates by analyzing device behaviors and network traffic patterns. The most important improvements are that this hybrid system maximizes the overall security and robustness of IoT ecosystems, offering scalable and adaptive protection against evolving malware threats. The proliferation of Internet of Things (IoT) devices has changed edge and fog computing environments, enabling real-time data processing and analysis at the source, but the decentralized and resource-constrained nature of these architectures exposes them to serious cybersecurity threats, especially malware attacks. New security frameworks have been introduced that combine trust management with advanced cluster learning techniques like XGBoost and AdaBoost to mitigate malware threats in IoT-powered edge fog environments. Experimental results show that combining trust-based security with machine learning-based malware detection dramatically increases the robustness of IoT ecosystems against malware, driving these resource efficiencies