AN ENSEMBLE INTRUSION DETECTION SYSTEM USING GRADIENT BOOSTING ALGORITHM FOR EDGE-BASED COMPUTING

Science and Tech

Intrusion detection systems (IDS) are essential for maintaining the security of edge computing environments, where traditional centralized approaches often fail to meet the demands for real-time processing and low latency. This paper proposes an Ensemble Intrusion Detection System (EIDS) using the Gradient Boosting Algorithm to enhance detection accuracy and performance in edge-based computing environments. The system’s effectiveness was evaluated against AdaBoost, another ensemble learning algorithm, using key performance metrics such as accuracy, recall, precision, F1-score, and time efficiency. The results indicate that Gradient Boosting achieved superior performance, with an accuracy of 97.68%, recall of 97.68%, precision of 97.69%, and an F1-score of 97.68%, while training in just 4.5 seconds. In contrast, AdaBoost achieved an accuracy of 95.85%, with a significantly longer training time of 58.0 seconds. Gradient boosting’s faster training time and higher accuracy make it a more suitable choice for real-time intrusion detection in edge computing environments. These findings highlight the potential of ensemble learning techniques, particularly gradient boosting, in enhancing the security and efficiency of edge-based systems.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.