An Enhanced DDoS Attack Detection in Software-Defined-Networks using Ensemble Learning

An Enhanced DDoS Attack Detection in Software-Defined-Networks using Ensemble Learning

연구 분야: Networking

학회: SN Computer Science

The rising danger of Distributed Denial of Service (DDoS) attacks in Software-Defined Networking (SDN) environments stresses advanced detection strategies to safeguard network availability and service integrity. By utilizing ensemble learning techniques, this study offers a novel method for the DDoS attack identification. Through the utilization of a diverse range of datasets including CICIDS 2017, KDDCup99, NSL-KDD99, Nisha Ahuja's dataset, and a dataset from Mouhammd Alkasassbeh's paper, this study demonstrates the adaptability and efficacy of ensemble learning across varied network scenarios. Various detection models are combined using ensemble learning techniques to produce a reliable and adaptable detection mechanism. The results manifest the superiority of the ensemble approach, showcasing enhanced accuracy, reduced false positives, and improved generalization across the datasets. This research offers insights into the intrinsic strengths of ensemble learning for DDoS attack detection, highlighting its ability to address the diverse array of threats posed in SDN environments. The findings provide valuable contributions to the realm of network security, paving the way for more resilient DDoS detection strategies in the ever-evolving landscape of software-defined networks.