Efficient Intrusion Detection for Smart Homes: Suricata and Machine Learning for Speed and Efficiency

Tumparthy, Navya (2024) Efficient Intrusion Detection for Smart Homes: Suricata and Machine Learning for Speed and Efficiency. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (8MB) | Preview

Abstract

Smart home devices and their integration with IoT has increased cyber-attacks significantly. Therefore, there is need for efficient Network Intrusion Detection systems (NIDS). Currently available IDS are not great because they produce number of false alarms and resource utilisation is high making them not suitable for smart homes where the computational power is limited. Hence, there is a need for Intrusion Detection Systems (IDS) that are quick in identifying attacks and use less computational resources. In this study, a hybrid machine learning model is integrated with Suricata to address the drawbacks of conventional IDS. Our model utilises the advantages of two algorithms, Random Forest (RF) for feature selection and LGBM (Lightweight Gradient Boost Model) for prediction. The models are trained on latest CICIoT2023 dataset and tested in a simulated smart home network by attack simulation. The enhanced model showed notable results especially with DDoS (Distributed Denial of Service), DNS tunnelling, and Mirai botnet attacks. Significant improvement in detection time and resource efficiency is observed. These studies provide notable advancement in IDS for real-time detections in resource constraint environments. Despite the success, the model needs performance improvement in few attack categories and analysis of commercial application is needed.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Hafeez, Khadija UNSPECIFIED
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QA Mathematics > Computer software > Computer Security T Technology > T Technology (General) > Information Technology > Computer software > Computer Security Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Cyber Security
Depositing User:	Ciara O'Brien
Date Deposited:	31 Jul 2025 11:57
Last Modified:	31 Jul 2025 11:57
URI:	https://norma.ncirl.ie/id/eprint/8381

Actions (login required)

View Item