The role of Large Language Models in IoT security: A systematic review of advances, challenges, and opportunities
Bibliographic record
Abstract
The Internet of Things (IoT) has revolutionized digital ecosystems by interconnecting billions of devices across various industries, enabling enhanced automation, real-time monitoring, and data-driven decision-making. However, this expansion has introduced significant security and privacy challenges due to the heterogeneous nature of IoT devices, resource constraints, and the decentralized nature of their architectures. Large Language Models (LLMs) have recently shown promise in improving cybersecurity by enabling automated threat intelligence, anomaly detection, malware classification, and privacy-aware security enforcement. Therefore, this systematic review investigates research published between 2015 and 2025 to examine the intersection of LLMs, IoT security, and privacy. We evaluate state-of-the-art LLM-based security frameworks, highlighting their effectiveness, limitations, and impact on IoT cybersecurity. In addition, this review identifies key research gaps and challenges, providing insight into the scalability, efficiency, and adaptability of LLM-driven security solutions. This work aims to contribute to the advancement of AI-driven IoT security frameworks, supporting the development of resilient and privacy-preserving cybersecurity architectures.
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 machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.010 | 0.040 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.004 | 0.004 |
| Bibliometrics | 0.005 | 0.005 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.003 | 0.005 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.004 | 0.001 |
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 source (direct Gemma or distilled Codex), 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".