Cyber Intrusion Detection in Protective Relays Using Deep Learning Attention-Based Models
Bibliographic record
Abstract
The increasing digitalization of modern substations has improved operational efficiency while simultaneously exposing protection schemes in digital substations to sophisticated cyber threats. This paper proposes an attention-based deep learning (DL) framework for enhancing the cybersecurity of transformer differential relays (TDRs), a highly critical yet vulnerable smart grid protective relay. Leveraging the DL transformer architecture, the proposed model is trained offline to distinguish manipulated TDR measurements from those corresponding to legitimate faults. It utilizes self-attention mechanisms to effectively capture temporal dependencies and complex correlations within the six-phase current measurements of the TDR, providing a robust layer of security against cyberattacks based solely on the TDR measurements. Experimental results demonstrate that the proposed Transformer-based model (1) achieves superior attack detection accuracy and lower false alarm rates compared to existing solutions, (2) does not deprive the TDR of its speed merit, and (3) has explainable predictions. These findings highlight the potential of attention-based architectures for developing intelligent cyber-resilient protective relays in smart grids.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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".