Edge AI Solutions for Real-Time IoT Device Threat Monitoring

The rapid proliferation of Internet of Things (IoT) devices across industrial, commercial, and consumer environments has significantly expanded the attack surface of modern networks. These devices often operate with limited computational resources, heterogeneous architectures, and minimal built-in security, making them prime targets for cyber threats such as malware infiltration, denial-of-service attacks, and data exfiltration. Traditional cloud-centric security approaches are hindered by latency, bandwidth constraints, and privacy concerns, limiting their ability to provide timely threat detection and response. Edge Artificial Intelligence (Edge AI) offers a transformative solution by enabling real-time threat monitoring directly on or near IoT devices, leveraging localized processing to analyze data streams, detect anomalies, and trigger rapid mitigation without relying on constant cloud connectivity. This paper presents a comprehensive study of Edge AI solutions for IoT threat monitoring, focusing on lightweight machine learning and deep learning models optimized for edge hardware such as microcontrollers, single-board computers, and dedicated AI accelerators. We explore architectural frameworks integrating Edge AI into IoT ecosystems, including distributed threat intelligence, on-device inference, and hybrid edge–cloud collaboration models. Emphasis is placed on anomaly detection, behavioral profiling, and federated learning techniques that enhance detection accuracy while preserving data privacy. Experimental evaluations on representative IoT security datasets, such as UNSW-IoT and BoT-IoT, demonstrate that Edge AI-based systems can achieve low-latency detection with competitive accuracy compared to cloud-based methods, while significantly reducing network overhead. We further discuss deployment challenges, including model compression, energy efficiency, adversarial resilience, and lifecycle management in dynamic IoT environments. The paper concludes by identifying future research opportunities in explainable Edge AI for security, multi-modal threat data fusion, and standardized evaluation benchmarks for real-time IoT threat monitoring. Our findings highlight that Edge AI, when strategically implemented, can play a pivotal role in securing IoT infrastructures by enabling scalable, low-latency, and privacy-preserving threat detection capabilities at the network edge.