AI/ML Conceptual Framework for Cyberthreat Detection for IoT-Based Cyber-Physical Systems

The growing integration of Internet of Things (IoT) technologies within cyber-physical systems (CPS) has enabled autonomous and monitoring applications ranging from self-navigating manufacturing robots to large-scale environmental sensing networks and smart grid applications. However, this rapid connectivity has also intensified cybersecurity threats and interoperability challenges. Recent studies report that IoT-based CPS cyberattacks have surged by more than 300% since 2020, with over 1.5 billion attempted breaches recorded in 2024. This research is a continuation of a previous study which explored the descriptive relationships between IoT-based CPS systems for the most common cyberthreats and design variables, specifically power consumption, data latency, data processing and data quality. Therefore, this study proposes an AI/ML conceptual framework for designing algorithms to identify different types of cyberthreats across three different layers of IoT-based CPS, namely the sensor layer, network layer and application layer. A structured literature review following the PRISMA framework is used to analyze a sample of n = 56 articles using thematic content analysis. The findings from the study highlight average variation benchmarked in previous studies for design variables across the three layers of CPS systems under different types of cybersecurity attacks. For example, one of the findings from the study highlights the 200 to 400% increase in power consumption and data latency from sensors under a side-channel attack on a smart grid. This study provides an AI/ML cyberthreat detection conceptual framework mapping variations in the design variables and highlighting architecture for autonomous alert and response for IoT-based CPS under different types of cyberattacks, which adds novelty to this research and can be empirically validated in future studies that may support the development of multivariate cyberthreat detection models.