article · Electronics
This review evaluates security mechanisms across the industrial Internet of Things ecosystem, drawing from research published between 2015 and 2024 across five digital repositories. Vulnerabilities within these industrial networks are classified into architectural design weaknesses and multifaceted connectivity issues. The work evaluates classical learning algorithms, blockchain, and quantum mechanisms for addressing these loopholes, noting that quantum-inclined cyber attacks present severe computational challenges that classical learning alone struggles to manage. Combining classical learning techniques with quantum mechanisms is identified as a promising route to achieve optimal security in these settings. Furthermore, available industrial datasets are identified to support researchers in validating models for improved prediction, accuracy, and operational decision-making.
As modern industrial operations increasingly rely on connected devices, critical infrastructure becomes vulnerable to sophisticated digital threats. Emerging cyber attacks powered by quantum computing could overwhelm existing protections. Understanding how to merge quantum mechanisms with machine learning helps industrial networks prepare stronger defences against advanced security breaches.
The work maps conceptual pathways for developing hybrid quantum and machine learning security tools for industrial network operators. Because this review focuses on synthesising literature, categorising vulnerabilities, and identifying datasets rather than testing a specific implementation, any commercialisation remains at an early exploratory stage.
AI-generated from the published abstract. Always read the original work before citing.
This article describes our point of view regarding the security capabilities of classical learning algorithms (CLAs) and quantum mechanisms (QM) in the industrial Internet of Things (IIoT) ecosystem. The heterogeneity of the IIoT ecosystem and the inevitability of the security paradigm necessitate a systematic review of the contributions of the research community toward IIoT security (IIoTsec). Thus, we obtained relevant contributions from five digital repositories between the period of 2015 and 2024 inclusively, in line with the established systematic literature review procedure. In the main part, we analyze a variety of security loopholes in the IIoT and categorize them into two categories—architectural design and multifaceted connectivity. Then, we discuss security-deploying technologies, CLAs, blockchain, and QM, owing to their contributions to IIoTsec and the security challenges of the main loopholes. We also describe how quantum-inclined attacks are computationally challenging to CLAs, for which QM is very promising. In addition, we present available IIoT-centric datasets and encourage researchers in the IIoT niche to validate the models using the industrial-featured datasets for better accuracy, prediction, and decision-making. In addition, we show how hybrid quantum-classical learning could leverage optimal IIoTsec when deployed. We conclude with the possible limitations, challenges, and prospects of the deployment.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.3390/electronics13214153
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
