A Smart Network Intrusion Detection System for Cyber Security of Industrial IoT
Bibliographic record
Abstract
In the industrial sectors, machines and sensors communicate with each other and with the control or central units through the Internet; this forms a network of Industrial devices called the Industrial Internet of Things (IIoT). IIoT is an emerging trend that generates big data which could be vulnerable to cyber-attacks. In the IIoT network, data and control instructions are usually flown through a Supervisory Control and Data Acquisition (SCADA) system. We propose to install a Network Intrusion Detection System (NIDS) between SCADA and IIoT devices to monitor real-time network traffic and detect cyber-attacks. Several deep learning algorithms can be used on a large dataset for intrusion detection. In this paper, we implement and compare three deep learning algorithms, namely, MultiLayer Perceptron (MLP), Fully Connected Deep Neural Network (FCNN), and Convolutional Neural Network (CNN), on two different datasets by varying the number of selected features for classifications using the XGBoost algorithm. The study shows that CNN with XGBoost is superior in its performance over other methods applied to NIDS. Our proposed methodology has proven to be effective regardless of the highly unbalanced dataset.
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 | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 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".