Defenses for Adversarial attacks in Network Intrusion Detection System - A Survey

Abstract

In Computer Security, Machine Learning has great impact in recent years. Ranging from spam filtering, malware analysis, and traffic analysis to network security usage of Machine Learning Algorithms are manifold. In the area of Network Security machine learning techniques are used especially in developing Intrusion Detection Systems. There are basically two kinds of IDSes are there and they are Host IDS and Network IDS. Even though ML techniques have greatly improved the efficiency of the IDSes, they are vulnerable to adversarial attacks which are designed and launched by adaptive adversaries who know the working principles of machine learning models. In recent years Adversarial Machine Learning has gained attention in the domain of machine learning where in which attackers exploit the inherent fallacies in the assumptions made in the machine learning models which are designed to classify one input from another. In the domain of network security especially in IDS, adversarial machine learning has not been surveyed in detail. To address this challenge an analysis of different defense mechanisms are done in this survey.