Detection of False Data Injection Attacks in Smart Grids: An Optimal Transport-Based Reliable Self-Training Approach
Bibliographic record
Abstract
Despite the success of data-driven methods in detecting false data injection (FDI) attacks, the remarkable progress is inseparable from massive labeled and class-balanced measurements. However, the collected measurement datasets in smart grids typically exhibit skewed class distributions and are partially labeled due to the expensive labeling costs. Learning from such non-ideal datasets undoubtedly results in the degenerated detection performance of the data-driven methods. To cope with this issue, we propose an optimal transport (OT)-based framework named DeSSW to promote the utilization of plentiful unlabeled measurements through the self-training technique, which improves the ability to identify FDI attacks by producing distinguishable representations for normal and attacked measurements in the feature space. Specifically, DeSSW consists of a novel re-weighting algorithm and a debiased self-training strategy. The re-weighting algorithm ensures high-confidence unlabeled measurements dominate the self-training procedure, and the debiased self-training strategy mitigates bias accumulation in the iterative self-training procedure. Extensive experiments demonstrate that DeSSW achieves superior detection performance when facing the combinatorial challenge of partially labeled and class-imbalanced measurements, even if the measurements are noisy.
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 | 0.006 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.002 | 0.002 |
| 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".