A Survey of Research in Cybersecurity and Cyber-Physical Systems

The rapid expansion of the Internet of Things (IoT) has introduced a new wave of convenience, automation, and data-driven insights across numerous domains, including healthcare, smart homes, industrial automation, and critical infrastructure. However, this growth has also broadened the attack surface, exposing IoT networks to a wide range of cyber threats. Traditional security mechanisms, originally designed for conventional IT systems, often fall short when applied to IoT due to the constraints of power, memory, and processing capabilities in edge devices. In such a landscape, Intrusion Detection Systems (IDS)—particularly those enhanced by machine learning (ML)—have emerged as a crucial line of defense. IDS tools can analyze traffic patterns, detect anomalies, and flag malicious behavior without requiring full device-side implementation. Given the scale and variability of IoT networks, data-driven models that can learn from historical data and adapt to evolving threats are increasingly in demand.