DETECTION AND ANALYSIS OF NETWORK TRAFFIC IN NETWORK FORENSICS USING MACHINE LEARNING

Abstract

In this study, an automated system that can gather and process network packets is built. Machine learning techniques are used to create a traffic classifier that divides packets into hazardous and non-malicious categories. In the past, several conventional strategies were used to classify the network utilising tools; however, this method combines machine learning, a study area that is currently active and has produced good results so far. The main goals of this article are to analyse and control intrusions while also monitoring traffic. The traffic data collection KDD is used to develop a traffic classification system based on features of observed network packets. This category will assist the IT administrators in identifying the undefined assault that is becoming more common in the IT environment. The proposed methodologies detailed in this research, which help in gathering network packets and detecting which attack was carried out in a certain network, apply the machine learning algorithm to differentiate between dangerous and normal packets. The main objective of this project is to provide a proactive network attack detection system using machine learning based classifiers that identified incoming packets and discriminated between harmful and non-malicious network packets using rules from the KDD dataset. The system is trained using the attributes of the NSL-KDD dataset.