False Data Detector for Electrical Vehicles Temporal-Spatial Charging Coordination Secure Against Evasion and Privacy Adversarial Attacks
Bibliographic record
Abstract
As the number of electric vehicles on roads significantly increases, spatial-temporal charging coordination mechanisms have been introduced for balancing charging demand and energy supply. However, electric vehicles could send false data, such as state-of-charge (SoC), to the charging coordination mechanism for gaining high charging priority illegally. Machine Learning models can be used to detect false data. However, in our application the detector is trained on a dataset that contains sensitive information, such as the locations and SoC values of the electric vehicles. Therefore, attackers could launch adversarial attacks against the detector, such as membership inference and model inversion, for revealing sensitive information on the drivers whose data are used to train the detector. Furthermore, attackers could launch evasion attacks against the detector by computing false SoC values that are classified benign by the detector. Addressing the three attacks simultaneously makes the problem more complicated because a countermeasure to one attack may degrade the model's accuracy and unintentionally make the model more susceptible to other attacks. Accordingly, in this paper, we propose a deep-learning training approach for false data detector in spatial-temporal charging coordination. Our approach can deal with the tradeoffs and balance the detector's accuracy and robustness against the adversarial attacks. Specifically, our approach combines three techniques, including mimic learning, dropout, and differential privacy, in a certain way that makes the detector highly accurate in detecting false data and also robust against adversarial attacks. To validate our approach, we have conducted a set of experiments and the given results demonstrate the robustness and accuracy of our detector.
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 | 0.003 | 0.012 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.001 | 0.003 |
| Open science | 0.002 | 0.003 |
| Research integrity | 0.001 | 0.002 |
| 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".