Network intrusion detection system by applying ensemble model for smart home

TLDR

The rapid growth of IoT smart homes expands the attack surface, making timely intrusion detection essential for secure environments. This study proposes NIDSE, an ensemble-based network intrusion detection system for smart homes, to identify device attacks. NIDSE employs a sequential XGBoost ensemble that iteratively corrects errors, evaluated on the IoT‑NI dataset containing host discovery, SYN, ACK, and HTTP flooding attacks. Cross‑validation results show the XGBoost classifier achieves 94 % micro‑average and 85 % macro‑average precision across nine attack types.

Abstract

The exponential advancements in recent technologies for surveillance become an important part of life. Though the internet of things (IoT) has gained more attention to develop smart infrastructure, it also provides a large attack surface for intruders. Therefore, it requires identifying the attacks as soon as possible to provide a secure environment. In this work, the network intrusion detection system, by applying the ensemble model (NIDSE) for Smart Homes is designed to identify the attacks in the smart home devices. The problem of classifying attacks is considered a classification predictive modeling using eXtreme gradient boosting (XGBoosting). It is an ensemble approach where the models are added sequentially to correct the errors until no further improvements or high performance can be made. The performance of the NIDSE is tested on the IoT network intrusion (IoT-NI) dataset. It has various types of network attacks, including host discovery, synchronized sequence number (SYN), acknowledgment (ACK), and hypertext transfer protocol (HTTP) flooding. Results from the cross-validation approach show that the XGBoosting classifier classifies the nine attacks with micro average precision of 94% and macro average precision of 85%.