An Intrusion Detection System for the Internet of Things Based on Machine Learning: Review and Challenges

An intrusion detection system (IDS) is an active research topic and regarded as one of the important applications machine learning. IDS a classifier that predicts class input records associated with certain types attacks. In this article, we present review IDSs from perspective We three main challenges IDS, in general, for Internet Things (IoT), particular, namely concept drift, high dimensionality, computational complexity. Studies on solving each challenge direction ongoing are addressed. addition, paper, dedicate separate section presenting datasets IDS. datasets, KDD99, NSL, Kyoto, presented. This article concludes elements high-dimensional awareness, awareness symmetric their effect need to be addressed neural network (NN)-based model IoT.