An Explainable Deep Learning System for Cyberattack Detection in Internet of Energy Networks
Bibliographic record
Abstract
The integration of smart devices and real-time analytics in the Internet of Energy (IoE) has enabled intelligent, data-driven energy systems but also introduced cybersecurity concerns. Addressing these concerns requires detection mechanisms that are not only accurate but also interpretable. This article proposes an explainable deep learning system, named E-SHIELD, designed to detect various cyberattacks in IoE networks. The system uses a hybrid Convolutional Neural Network—Long-Short-Term Memory (CNN-LSTM) architecture to learn both spatial correlations and temporal dependencies from network traffic data. The architecture is optimized for resource-constrained environments by using compact filters, dropout regularization, and low learning rates. E-SHIELD is evaluated using two benchmark datasets, WUSTL-IIoT-2021 and CICIoT-2023, which contain diverse real-world attack scenarios such as Denial of Service (DoS), Distributed DDoS, Mirai variants, and fuzzing attacks. To ensure transparency, SHAP (SHapley Additive exPlanations) is integrated to provide both global and local interpretability of the model’s predictions. A user dashboard has been developed to support human-in-the-loop monitoring, allowing users to analyze predictions, feature importance, and risk levels in real-time. Experimental results show that the E-SHIELD system achieves high accuracy compared to existing CNN, LSTM, and ensemble-based models. By combining robust detection capabilities with interpretable AI, E-SHIELD supports secure and trustworthy deployment in mission-critical energy systems.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| 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) | 0.000 | 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 teacher head, 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".