MALICIOUS THREAT DETECTION FOR THE NAVFAC-BASED SMART GRID NETWORK USING BAYESIAN CLASSIFICATION AND MACHINE LEARNING
Bibliographic record
Abstract
With the Navy's focus on efficient energy consumption, Naval Facilities Engineering Command deployed its own Smart Grid in 2019, allowing shore commands to modernize and meet energy consumption mandates set in place by the Secretary of the Navy. With the addition of new 'smart' technology comes additional risks in the form of cyber-attacks. This thesis implements a Bayesian classification and machine learning algorithm that explores how the data set, size of training data and number of features affect classification accuracy. Our experiment was performed using seven data sets, developed through the University of Montreal using a SCADA sandbox similar to that of the Navy Smart Grid. Three data sets contained nominal data, and four data sets contained malicious cyber-attacks. Our experiments, performed using MATLAB, showed that malicious packet distribution within the data set and size of the training data greatly affected classification accuracy. This thesis demonstrates machine learning operability for use in the Smart Grid environment and will provide data points to further research for Network Intrusion Detection Systems (NIDS).
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 | 0.002 | 0.008 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 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".