Ensemble Feature Learning-Based Event Classification for Cyber-Physical Security of the Smart Grid
Bibliographic record
Abstract
The power grids are transforming into the cyber-physical smart grid with increasing two-way communications and abundant data flows. Despite the efficiency and reliability promised by this transformation, the growing threats and incidences of cyber attacks targeting the physical power systems have exposed severe vulnerabilities. To tackle such vulnerabilities, intrusion detection systems (IDS) are proposed to monitor threats for the cyber-physical security of electrical power and energy systems in the smart grid with increasing machine-to-machine communication. However, the multi-sourced, correlated, and often noise-contained data, which record various concurring cyber and physical events, are posing significant challenges to the accurate distinction by IDS among events of inadvertent and malignant natures. Hence, in this research, an ensemble learning-based feature learning and classification for cyber-physical smart grid are designed and implemented. The contribution of this research are (i) the design, implementation and evaluation of an ensemble learning-based attack classifier using extreme gradient boosting (XGBoost) to effectively detect and identify attack threats from the heterogeneous cyber-physical information in the smart grid; (ii) the design, implementation and evaluation of stacked denoising autoencoder (SDAE) to extract highlyrepresentative feature space that allow reconstruction of a noise-free input from noise-corrupted \nperturbations; (iii) the design, implementation and evaluation of a novel ensemble learning-based feature extractors that combine multiple autoencoder (AE) feature extractors and random forest base classifiers, so as to enable accurate reconstruction of each feature and reliable classification against malicious events. The simulation results validate the usefulness of ensemble learning approach in detecting malicious events in the cyber-physical smart grid.
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| 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 | 0.000 | 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".