A Hybrid Machine Learning-Based Smart Home IoT Security System for Threat Detection, Classification, and Alert Mechanisms

Multiclass Cyber Attack Classification in Smart Home IoT Networks Using Ensemble Machine Learning with the ML-EdgeIIoT Dataset

A machine learning-based intrusion detection framework for multiclass classification of eight categories of IoT network attacks, namely Backdoor, MITM, DDoS, Ransomware, Password Attack, SQL Injection, Prob-attacks, and Normal traffic is designed and evaluated while minimizing false positives and false negatives.

Enhancing IoT Smart Home Security Through Machine Learning-Based Cyberattack Detection: A Comparative Evaluation

Smart homes depend on interconnected sensors, cameras, routers, mobile applications, and cloud services. This connectivity improves automation and convenience, but it also expands the attack surface for Distributed Denial of Service (DDoS), Denial of Service (DoS), Mirai botnet, brute-force, spoofing, reconnaissance, and man-in-the-middle attacks. Traditional signature-based security is often insufficient because IoT devices are resource-constrained, heterogeneous, and frequently deployed with weak authentication or delayed firmware updates. This study evaluates supervised machine-learning classifiers for detecting cyberattacks in smart-home IoT network traffic using the CICIoT2023 dataset. Four algorithms, namely Random Forest, Decision Tree, k-Nearest Neighbour, and Support Vector Machine, were compared under 50:50, 70:30, and 80:20 train-test split settings. The models were evaluated using accuracy, precision, recall, and F1-score, with emphasis on DDoS, Mirai, and brute-force attack classes that are particularly relevant to smart-home environments. The findings show that tree-based classifiers are highly effective for IoT attack detection. Random Forest achieved the strongest overall accuracy and precision, while Decision Tree showed the most stable recall and F1-score for brute-force detection. The results indicate that Random Forest is suitable as a general-purpose smart-home IDS classifier, whereas Decision Tree or a hybrid ensemble strategy should be considered when missed brute-force attacks carry high operational risk. The paper contributes a clearer empirical comparison of lightweight supervised learning models and provides implementation guidance for smart-home intrusion detection systems.

Review of Machine Learning Intrusion Detection Systems in Internet of Things Environment

The use of Internet of Things (IoT) technology entails incorporating numerous devices into heterogeneous networks, which is done in order to provide intelligence as well as automation in services. Yet, increased connectivity also poses various issues relating to the cyber-security of these networks, and resource-constrained nature of IoT devices hampers the effectiveness of conventional cyber-security techniques due to evolving threats. Intrusion Detection Systems (IDSs) has become an integral part of IoT network security. The purpose of this research is to analyze Machine Learning (ML)-based approaches to detect cyber-attacks in the environment of IoT. The review includes the types of learning approaches that were used in studies on existing IDSs, classifiers, databases, the types of attacks and anomalies detected, techniques to select features, as well as methods for evaluation of IDS. Thus, the analysis demonstrates that using machine learning enables to detect a variety of cyber-attacks and anomalies. Still, there are some barriers, such as imbalanced and small-size database, feature redundancy, computational constraints, false positives, and identification of new attacks. Thus, the review highlights the benefits and draw backs of currently existing IDS based on machine learning and proposes possible areas for future studies.

AI-Driven Intrusion Detection and Energy-Efficient Routing in Internet of Things (IoT) Networks

Adaptive Machine Learning Framework for Real-Time Cyber-Attack Detection and Prevention in IoT Networks

This paper introduces an innovative ML-based security paradigm that improves the attack detection accuracy by combining adaptive feature extraction techniques with a context-attentive hybrid mechanism and maximizes detection accuracy and computational efficiency.

Hybrid Intrusion Detection System with Real-Time Concept Drift Detection for Enhanced IoT Security

A hybrid IDS framework that integrates supervised Random Forest classification, unsupervised Isolation Forest anomaly monitoring, and Kolmogorov–Smirnov (KS)-based concept drift monitoring is presented, providing initial evidence of generalization to one held-out attack family but should not be interpreted as proof of broad zero-day detection capability.