Machine Learning for Intrusion Detection in IIoT: A Comprehensive Review
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
In recent years, the Industrial Internet of Things (IIoT) has grown rapidly, with the potential to transform and connect many industries, opening up major opportunities for the global economy. IIoT extends to industries such as manufacturing, logistics, transportation, energy, oil and gas, mining and aviation. However, despite its advantages, the IIoT is exposed to increasing cyber attacks due to the large amount of data generated by its many sensors. These attacks create an increased need for advanced security solutions. Intrusion detection systems (IDS), which monitor network traffic and identify abnormal behavior, are essential to protect IIoT networks. Machine learning (ML) is an effective solution to improve IDS performance by enabling proactive intrusion detection. This literature review explores ML-based detection techniques, highlighting supervised, unsupervised and deep learning methods. The main objective of this research is to present and analyze different approaches of machine learning applied to intrusion detection in IIoT, as well as the data sets used and comparative results obtained in existing studies. We also highlight the challenges and limitations of these approaches, such as managing resources, reducing false positives and adapting to new threats. This review concludes that the use of supervised or hybrid models and solutions, such as supervised or federated learning, could improve the security of IIoT systems. Finally, this research provides future directions to overcome the challenges of model scalability and optimization in order to better meet the increasing safety requirements in industrial environments.
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.
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 | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.003 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 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 it