Intrusion Detection and Identification System Design and Performance Evaluation for Industrial SCADA Networks
Bibliographic record
Abstract
Industrial SCADA networks are subject to cyber-attacks that have the potential to cause significant disruption, damage, and havoc. In this paper, we present a study that proposes a three-stage classifier model which employs a machine learning algorithm to develop an intrusion detection and identification system for tens of different types of attacks against industrial SCADA networks. The machine learning classifier is trained and tested on the data generated using the laboratory prototype of a gas pipeline SCADA network. The dataset consists of three attack groups and seven different attack classes or categories. The same dataset further provides signatures of 35 different types of attacks which are related to those seven attack classes. The study entailed the design of three-stage machine learning classifier as a misuse intrusion detection system to detect and identify specifically each of the 35 attack types. The first stage of the classifier decides if a record is associated with normal operation or an attack signature. If the record is found to belong to an attack signature, then in the second stage, it is classified into one of seven attack classes. Based on the identified attack class as determined by the output from the second stage classifier, the attack record is provided for a third stage attack type classification, where seven different classifiers are employed. The output from the third stage classifier identifies the attack type to which the record belongs. Simulation results indicate that designs exploring specialization to domains or executing the classification in multiple stages versus single-stage designs are promising for problems where there are tens of classes. Comparison with studies in the literature also indicated that the multi-stage classifier performed markedly better.
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 | 0.003 | 0.007 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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 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".