IoT

The Industrial Internet of Things (IIoT) instruments physical processes with networked sensors and controllers that stream multivariate telemetry, and monitoring this telemetry for faults and cyberattacks is essential to reliability and safety. Machine learning is the natural tool, but failures are rare and seldom labeled, so supervised detection is impractical: a detector must learn normal behavior from unlabeled telemetry alone. In cyber-physical systems, this normal law is structured: a union of many imbalanced operating regimes shaped by physics and control, formalized as ten Massive, Implicit, Imbalanced Multimodality (MIIM) assumptions. That structure exposes a blind spot of the dominant approach: a fault can be individually normal on every sensor and reconstruct accurately, yet improbable under normal joint operation, so reconstruction-based detectors measure reachability rather than probability and miss it. Our detector, LatAD (Latent-density Anomaly Detector), learns a latent Gaussian-mixture clustering of regimes (VaDE, Variational Deep Embedding), scores anomalies by density, and factorizes that density over correlation-community subsystems combined by a cohesion-weighted Higher Criticism statistic. On three real IIoT testbeds, LatAD attains the best All-subset AUROC of any learned detector on HAI (0.948) and leads the difficult subset on HAI (0.845; a significant +0.088, 95% CI [0.042, 0.157]); USAD and TranAD fall to 0.44–0.50 on these reconstructable-but-improbable faults.

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.

Various competing wireless technologies claim superior long-range performance at low power budgets. However, it is difficult for system designers to select the appropriate technologies for their applications. Consequently, to guide such selections, this paper presents characteristic measurement data for three noted technologies: LoRaWAN, mioty, and Wi-Fi HaLow. The introduced measurement setups enable evaluation of the technologies with respect to energy consumption, sensitivity, and network performance in indoor environments. Based on the quantitative results, we discuss the individual strengths of the evaluated technologies. Supportive plots provide system designers with essential information to select the most appropriate wireless technology for their applications and avoid poor decision-making.