Evaluation of machine learning algorithms for intrusion detection system

TLDR

Intrusion detection systems defend against attacks, but attackers constantly evolve their tools, making effective IDS implementation challenging. The study evaluates multiple machine learning classifiers on the KDD intrusion dataset to determine their suitability for IDS. The authors computed false‑negative and false‑positive rates, along with other performance metrics, to assess each classifier’s detection capability. Decision table achieved the lowest false‑negative rate, while random forest attained the highest average accuracy.

Abstract

Intrusion detection system (IDS) is one of the implemented solutions against harmful attacks. Furthermore, attackers always keep changing their tools and techniques. However, implementing an accepted IDS system is also a challenging task. In this paper, several experiments have been performed and evaluated to assess various machine learning classifiers based on KDD intrusion dataset. It succeeded to compute several performance metrics in order to evaluate the selected classifiers. The focus was on false negative and false positive performance metrics in order to enhance the detection rate of the intrusion detection system. The implemented experiments demonstrated that the decision table classifier achieved the lowest value of false negative while the random forest classifier has achieved the highest average accuracy rate.