A Survey of Machine Learning Approaches to IoT Security
Algorithms · 11.05.2026 · 19 (5) · 384
DOI: 10.3390/a19050384 ↗Kurz gefasst
Fachartikel in der Zeitschrift Algorithms, online erschienen am 11.05.2026. Verfasst von Iosef Georgian und 3 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 67 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: POLITEHNICA Bucharest, European Commission, CHIPS Joint Undertaking, Ministry of Research, Innovation, and Digitization, CNCS/CCCDI-UEFISCDI.
Abstract (Originalsprache)
The explosive growth of the Internet of Things (IoT) has expanded the attack surface across industrial systems, smart cities, healthcare, and homes, motivating a synthesis of recent advances in machine learning for IoT security and a clear statement of remaining gaps. This review conducted a systematic search of MDPI, IEEE Xplore, Nature, ScienceDirect, and SpringerLink for publications from 2023 to 2025, screening them for domain relevance and organizing findings into a taxonomy of ML methods, threat types, and deployment contexts, with particular attention to datasets, edge constraints, and privacy considerations. We find that the field is shifting from signature-based detection to supervised and deep learning approaches that report high accuracy on benchmark traffic, while federated learning enables privacy-preserving, distributed intrusion detection with near-real-time edge performance. Across domains, prevalent threats include DDoS, unauthorized access, and malware; persistent challenges include device heterogeneity, rapid exploit weaponization, nonstandardized evaluation, concept drift, adversarial/poisoning risks, and governance and privacy constraints that hinder real world rollouts. We conclude that ML materially strengthens IoT resilience but requires rigorous, industry-scale validation, lightweight and explainable models, protocol-aware designs, robust federated aggregation, and SDN/NFV orchestration; we outline benchmark and deployment priorities to translate laboratory gains into operational security.
Förderung
- POLITEHNICA Bucharest
- European Commission, CHIPS Joint Undertaking
- Ministry of Research, Innovation, and Digitization, CNCS/CCCDI-UEFISCDI
Zitieren
APA
Georgian, I., Zamfirel, T. A., Goga, N., & Crăciunescu, R. (2026). A Survey of Machine Learning Approaches to IoT Security. Algorithms, 19(5), 384. https://doi.org/10.3390/a19050384
Vancouver
Georgian I, Zamfirel TA, Goga N, Crăciunescu R. A Survey of Machine Learning Approaches to IoT Security. Algorithms. 2026;19(5):384. doi:10.3390/a19050384
BibTeX
@article{Georgian2026,
author = {Georgian, Iosef and Zamfirel, Teșulă Adrian and Goga, Nicolae and Crăciunescu, Răzvan},
title = {A Survey of Machine Learning Approaches to IoT Security},
journal = {Algorithms},
year = {2026},
volume = {19},
number = {5},
pages = {384},
doi = {10.3390/a19050384}
}
EUVIMED