Hardware in loop simulation of replay attacks on synchrophasor data and detection using machine learning approach
Bibliographic record
Abstract
In the 21stcentury, the power system has integrated large-scale communication technology with existing infrastructure, enabling wide-area monitoring, protection, and control (WAMPAC) applications. Though this has enhanced the grid’s reliability, stability, security, and operations, it has also increased its dependency on communication networks, resulting in new cybersecurity issues. Among various cyber-attacks, Replay attacks have received less attention due to their similarity to healthy scenarios, making them difficult to detect. This article presents a machine learning (ML) approach using Random Forest (RF) to detect Replay attacks in Synchrophasor data. The method classifies data as either "Healthy" or "Replay-attack" by extracting statistical features such as mean, standard deviation, variance, skewness, kurtosis and auto-correlation. The algorithm’s effectiveness is evaluated by comparing different metrics with models like Support Vector Machines (SVM) andk-Nearest Neighbour(k-NN). To validate the proposed method, a Hardware-in-the-Loop (HIL) cyber-physical testbed was developed, and various datasets for training and validation were generated. Synchrophasor data, from a Phasor Measurement Unit (PMU) to a Phasor Data Concentrator (PDC), are generated using network emulation software containing both healthy cases and attack scenarios. The comparative analysis of the results demonstrates that the proposed model outperforms SVM andk-NN, thereby accurately detecting Replay attacks.
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) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 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".