ANALYSIS AND DETECTION OF INTRUSION DETECTION ON NETWORK SECURITY ENVIRONMENT USING ML

The Intrusion Detection System (IDS) is a critical cyber security instrument that monitors and detects intrusion threats. This research intends to examine contemporary IDS research utilizing a Machine Learning (ML) methodology, with a focus on datasets, ML algorithms, and metrics. The choice of datasets is critical for ensuring that the model is suitable for IDS use. Traditional methods, such as firewalls, which focus on data filtering, may not be adequate for detecting all forms of assaults in a timely manner. Machine learning algorithms-based on intrusion detection systems (IDS) are especially good in efficiently processing vast amounts of data in order to identify any malicious behavior for effective handling and prompt detection of these types of attacks. Machine learning-based intrusion detection systems (IDS) are used to monitor all network traffic for malicious activity. In order to improve the intrusion detection system’s detection rate, the system’s focus was on false negative and false positive performance measures. The results of this paper showed that the ML model XGBoost classifier had the best accuracy rate, while the Decision tree classifier had the lowest.