Implementation of a multi-stage intrusion detection systems framework for strengthening security on the internet of things

Abstract

The Internet of Things (IoT) expansion has introduced a new era of interconnectedness and creativity inside households. Various independent gadgets are now controlled from a distance, enhancing efficiency and organization. This results in increased security risks. Competing vendors rapidly develop and release novel connected devices, often paying attention to security concerns. As a result, there is a growing number of assaults against smart gadgets, posing risks to users' privacy and physical safety. The many technologies used in IoT complicate efforts to provide security measures for smart devices. Most intrusion detection methods created for such platforms rely on monitoring network activities. On multiple platforms, intrusions are challenging to detect accurately and consistently via network traces. This research provides a Multi-Stage Intrusion Detection System (MS-IDS) for intrusion detection that operates on the host level. The study employs personal space and kernel space data and Machine Learning (ML) methods to identify different types of intrusions in electronic devices. The proposed MS-IDS utilizes tracing methods that automatically record device activity, convert this data into numerical arrays to train multiple ML methods, and trigger warnings upon detecting an incursion. The research used several ML methods to enhance the ability to see with little impact on the monitoring devices. The study evaluated the MS-IDS approach in a practical home automation system under genuine security risks.