Fuzzy-Xgboost: A Fuzzy Basedextreme Gradient Boostermethodology for the Anomalyintrusion Detection in the 5G-SDN

Intrusion detection is one of the prime research areas in developing a effectiveSDN environment. The ever increasing demand in the network, has directlyincreased the malicious activity and cyber threats in the 5G networks. Variousresearch done in the area of intrusion detection has more room for improvement,by including the machine learners in the IDS development. In this work,a Intrusion Detection System (IDS) is developed for the SDN by including wellknown machine learners and tree based algorithms. The entire process is done asData preprocessing,Feature extraction,Dimensionality reduction & Classification.Well known NSL-KDD data set is considered for this research. Random forestclassifier aids in the feature extraction, and the principal component analysis(PCA) for the dimensionality reduction. A Fuzzy-XGBooster classifier is proposedin this work, and it handles the classification part, and detects the normaland the anomaly class. The implementation part is done on the NSL-KDD dataset, and the performance is evaluated on several metrics. The proposed Fuzzy-XGBoost classifier achieved higher performance rate with the values of 0.999246for accuracy, 0.998859 for precision, 0.998716 for recall, 0.998788 for F1 measure,0.999485 for specificity, and 0.000515 for False Alarm rate respectively. Againfor the metrics MCC, NPV, FPR, FNR, PPV, RMSE, and MAE the proposedFuzzy-XGBoost classifier has achieved suitable values as 0.9981, 0.9993, 0.000602,0.001317, 0.9988, 0.029031, and 0.000843 respectively.