A Feasibility Area Approach for Early Stage Detection of Stealthy Infiltrated Cyberattacks in Power Systems
Bibliographic record
Abstract
Advanced stealthy cyberattacks are capable of infiltrating the cybersecurity layers of power grids and alter their operating conditions, resulting in adverse effects on the system performance. Detecting such Stealthy Infiltrated Cyberattacks (SICA) at the earliest opportunity becomes crucial in order to enable power system operators to implement appropriate corrective measures. To that end, this paper proposes the addition of a new cybersecurity layer for SICA after they have broken through existing cyberattack prevention layers. The paper develops the Feasibility Area (FA) as a classifier mechanism to detect SICA in the collected data of Power System State Variables (PSSV). The proposed detection layer consists of two computational stages. The first stage involves estimating the FA parameters through a historical window of data over a specified period of time, which is then inputted to the second stage. In the second stage, the position of each PSSV with respect to the estimated FA is assessed and utilized by the SICA detection mechanism to identify broken through attacks. A flag vector is created indicating the location of each PSSV with respect to the defined FA. The location of each PSSV and its pattern represented in the flag vector are utilized to identify the existence of SICA. Various SICA detection mechanisms using mathematical techniques and the Pattern Recognition Neural Network (PRNN) have been applied. The numerical results from the evaluation of the proposed FA approach demonstrate a promising performance in detecting the SICA using the proposed method.
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 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".