Intrusion Detection with Interpretable Rules Generated Using the Tsetlin Machine

Abstract

The rapid deployment in information and communication technologies and internet-based services have made anomaly based network intrusion detection ever so important for safeguarding systems from novel attack vectors. To this date, various machine learning mechanisms have been considered to build intrusion detection systems. However, achieving an acceptable level of classification accuracy while preserving the interpretability of the classification has always been a challenge. In this paper, we propose an efficient anomaly based intrusion detection mechanism based on the Tsetlin Machine (TM). We have evaluated the proposed mechanism over the Knowledge Discovery and Data Mining 1999 (KDD'99) dataset and the experimental results demonstrate that the proposed TM based approach is capable of achieving superior classification performance in comparison to several simple Multi-Layered Artificial Neural Networks, Support Vector Machines, Decision Trees, Random Forest, and K-Nearest Neighbor machine learning algorithms while preserving the interpretability.