2024 · 11 citations · 9 references
ComputingComputer ScienceCybersecurityComputer SecurityInternet Of ThingsMachine LearningDecision TreesEnsemble LearningEnsemble MethodsIntrusion DetectionIot SecurityThreat DetectionEnsemble Methods For Intrusion DetectionIot Attack Surface AnalysisIot Intrusion DetectionMachine Learning ClassificationMachine Learning For Intrusion DetectionMachine Learning For IotMachine Learning-based ClassificationRandom Forest Classification
As the Internet of Things (IoT) continues to expand its footprint across various sectors, including healthcare, industrial automation, and smart homes, the security of these interconnected devices becomes paramount. With the proliferation of IoT devices, the attack surface for potential cybersecurity threats has significantly increased, necessitating the development of efficient Intrusion Detection Systems (IDS). This study embarks on a comprehensive examination of several machine learning algorithms aimed at enhancing the prediction accuracy of IDS within IoT networks. Leveraging the ToN-IoT dataset, we implement and compare the effectiveness of models. The findings reveal that ensemble methods, particularly Random Forest and XGBoost, exhibit superior performance, underscoring their potential for deployment in safeguarding IoT ecosystems against malicious intrusions.
9
IoT Security: Ongoing Challenges and Research Opportunities
Zhikai Zhang, Michael Cheng Yi Cho, Chia‐Wei Wang et al. · 2014 · 721 citations
Internet of Things: Evolution, Concerns and Security Challenges
Parushi Malhotra, Yashwant Singh, Pooja Anand et al. · Sensors · 2021 · 249 citations · Full text
Using machine learning to secure IoT systems
Janice Canedo, Anthony Skjellum · 2016 · 204 citations
Detection of Unauthorized IoT Devices Using Machine Learning Techniques
Yair Meidan, Michael Bohadana, Asaf Shabtai et al. · arXiv (Cornell University) · 2017 · 198 citations · Full text