Detection of Distributed Denial of Charge (DDoC) Attacks Using Deep Neural Networks With Vector Embedding
Bibliographic record
Abstract
Charging coordination mechanisms have been adopted to avoid overloading the power grid and long waiting times for electric vehicles’ (EVs) drivers at charging stations. However, adversaries could launch distributed denial of charge (DDoC) attacks against charging stations by submitting fake charging requests to reserve charging time slots. The current mechanisms in the literature postulate that the requests reported by the EVs are valid and the detection of the DDoC attacks have not been well investigated yet. In this paper, we first evaluate the ability of DDoC attacks to disrupt the charging coordination mechanisms, and propose detectors to identify the attacks using deep neural networks with vector embedding. The detection methodology is based on capturing any anomalous behavior that deviates from the normal patterns of the station’s charging demand. For training and evaluating our detectors, we build a benign charging demand dataset using real vehicles’ routes and EVs’ technical parameters. After that, we introduce several attacks and use them to generate the malicious dataset. We analyze the dataset and find temporal and spatial correlations that can be exploited to detect DDoC attacks. To accurately detect the attacks, a vector embedding layer is combined with a deep neural network to capture/learn the spatial-temporal correlations within the charging requests. Performance evaluations demonstrate that the proposed detectors have high performance regarding the detection and false alarm rates.
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) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 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".