Intrusion Detection and Prevention System to Analyse and Prevent Malware using Machine Learning

Abstract

Computer security has become a potential challenge for all of the studies that have been conducted in communication and information technology domain. In order to guarantee a degree of safety that satisfies the needs of contemporary living, several instruments and procedures have been developed Among them, Intrusion Detection and Prevention Systems (IDPS) frequently detects network attacks and vulnerable behaviours that can reduce the system's efficient operation. This study focuses on designing and implementing an IDPS using NIDS and Docker Jail system with the help of KDDCup 1999 Dataset. Dimension reduction is achieved using PCA. The project's classification algorithms are the supervised SVM and KNN algorithms. In order to stop the attack, a HoneyPot, preferably Artillery, is used in conjunction with the Docker jail system, which is based on the FreeBSD and BSD jail system.