Design of A Distributed Intrusion Detection System for Streaming Data in IoT Environments

Nowadays, IoT devices produce a large amount of streaming data that requires real-time analysis to ensure its security. Traditional security solutions are no longer sufficient to counter recent IoT attacks and to analyze the huge amount of data. In recent years, intrusion detection systems have been the subject of much research to evaluate their performance in detecting intrusions in IoT, especially since they are based on Artificial Intelligence and allow real-time intrusion detection. In this paper, we present the architecture of an intrusion detection system for streaming data analysis. We implemented our IDS in a Fog computing architecture and developed using Apache Spark. We applied several machine-learning algorithms to the NF-ToN-IoT-v2 dataset, and the results were promising.