Edge AI Solutions for Real-Time IoT Device Threat Monitoring
Bibliographic record
Abstract
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.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.006 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.006 | 0.003 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.002 | 0.005 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".