Monitoring Network Traffic for Suspicious Activity

Abstract

An intrusion detection system investigates hostile behavior within a network or an approach. Software or a gadget called intrusion detection scans a network or system for an untrustworthy action. As computer connectivity increases, intrusion detection becomes increasingly important for network security. Many Intrusion Detection Systems have been built to defend the networks using statistical and machine learning technologies. Accuracy is a crucial factor in how well an intrusion detection system performs. To decrease false detections and boost detection rates, the accuracy of intrusion detection needs to be improved. In recent works, many strategies have been employed to enhance performance. The Intrusion detection system’s primary task is to analyze network traffic data. To solve this problem, a structured classification system is needed. This problem is approached in the suggested manner. Classification methods are often used to address related issues. NSL-KDD knowledge discovery Dataset is used to evaluate the results of these systems. This research aims to find an efficient classifier that detects anomaly traffic with a high accuracy level and minimal error rate by experimenting with possible machine-learning techniques.