CNN-BiLSTM-Based Classification of RPL Attacks in IoT Smart Grid Networks (Industry Track)
Bibliographic record
Abstract
The widespread integration of Internet of Things (IoT) technology in modern electrical power grids has given rise to the emergence of Industrial IoT Smart Grid Networks. However, the utilization of the Routing Protocol for Low-Power Lossy Networks (RPL) in IIoT Smart Grid Networks exposes them to significant risks of routing attacks due to their global connectivity and resource limitations. This paper proposes a hybrid deep neural network approach that utilizes the CNN-BiLSTM network for the detection and classification of attacks in the RPL protocol of IoT Smart Grid Networks. Relevant preprocessing and feature enhancement techniques are applied to engineer and enhance pertinent features. The Synthetic Minority Oversampling Technique (SMOTE) is employed to address the data imbalance problem. The performance of the proposed approach is evaluated and compared with seven different deep learning and traditional classification algorithms on two scenarios. First, we simulate an IIoT network and various types of attacks mentioned in [6]. The results demonstrate the superior performance of the CNN-BiLSTM based approach, achieving an accuracy of 91%, precision of 89%, and recall of 89% in detecting various RPL attacks. Next, we apply the proposed approach to another dataset collected from nine commercial IoT devices infected by two botnets [19]. The approach outperforms other machine learning-based approaches with an accuracy of 90%, precision of 89%, recall of 90%, and F1-score of 89%, which demonstrates the practical applicability of the proposed approach in real-world industrial settings.
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 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 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".