ABSTRACT
In today’s cyber world, the demand for the internet is increasing day by day, thereby increasing the concern of network security. Intrusion Detection System (IDS) is meant to be a software application which monitors the network or system activities and finds out if any malicious operations occur. Tremendous growth and usage of internet raises concerns about how to protect and communicate the digital information in a safe manner. Hackers use different types of attacks for getting the valuable information these days. The aim of an Intrusion Detection System (IDS) is to provide approaches against many fast-growing network attacks (e.g., DDoS attack, Ransomware attack, Botnet attack, etc.). The study evaluates performance analysis of ten (10) different machine learning models for intrusion detection system. These models are Gradient Boosting, Xgboost, Lightgbm, Support Vector Machine, K Nearest Neighbor, Decision Tree, Random Forest, Logistic Regression, Gaussian NB, Bernoulli NB. In addition to using evaluation metrics such as accuracy, precision, recall, F1-score, the study used Mean precision, Mean recall, Macro average recall, Weighted average recall, Macro average precision, Weighted average precision, Macro average support and weighted average support were implemented in the analysis. The study made use of the KDD dataset. The best performing machine learning models in terms of accurate results were obtained from GRADIENT BOOSTING, XGBOOST and LIGHTGBM.
