Detecting web attacks using random undersampling and ensemble learners

Abstract Class imbalance is an important consideration for cybersecurity and machine learning. We explore classification performance in detecting web attacks the recent CSE-CIC-IDS2018 dataset. This study considers a total of eight random undersampling (RUS) ratios: no sampling, 999:1, 99:1, 95:5, 9:1, 3:1, 65:35, 1:1. Additionally, seven different classifiers are employed: Decision Tree (DT), Random Forest (RF), CatBoost (CB), LightGBM (LGB), XGBoost (XGB), Naive Bayes (NB), Logistic Regression (LR). For metrics, Area Under Receiver Operating Characteristic Curve (AUC) Precision-Recall (AUPRC) both utilized to answer following three research questions. The first question asks: “Are various ratios statistically from each other attacks?” second And, our third “Is interaction between significant Based on experiments, answers all questions “Yes”. To best knowledge, we apply techniques dataset while exploring sampling ratios.