Snort for Intrusion Detection in Internet of Things Network: A Study Using Machine Learning Approach

Abstract

The extending vogue of network attacks impacts the availability, confidentiality, and integrity of critical information in all types of network. Some typical network like Internet of things (IoT) can can have fatal consequences as a result of network attacks. With the growth in the usage of Internet of Things devices in the existing network, their vulnerability to a vast range of cyber attacks becomes a prime concern. The, Intrusion Detection Systems (IDS) have been used since long as a defense to identify the attacks and secure the network from intrusions. However, the existing IDS may be less effective in handling the rising attacks and threats in IoT network and machine learning based IDS can provide a more efficient solution. Snort has been used since more than 2 decades for detecting network attacks in various applications. Thus, in this work we study machine learning algorithms to explore their suitability for use in snort in attack detection for IoT traffic. We also propose a model that integrates the snort with machine learning algorithms for attack detection in IoT network traffic.