Implementation of Two-Layer Feature Selection and Optuna Framework for Predicting Cyberattacks in Internet of Things Networks
Bibliographic record
Abstract
Internet of Things (IoT) is rapidly expanding and becoming vital in many aspects of human life. This expansion also increases the risk of cyberattacks. Therefore, predicting these threats is crucial. Machine learning-based prediction models have become the most recent approaches for addressing these threats. However, the dataset size and default parameters employed in the model may impact poor performance. In this study, we aim to develop a cyberattacks prediction model using two-layer feature selection and the Optuna framework. The filterbased approach, i.e., Pearson Correlation, initially selects features instantly in the first layer. Then, in the second layer, these features are reselected using a wrapper and embedded approach based on their contribution to the model. In addition, Optuna, the define-by-run framework for hyperparameter tuning, is employed to determine the best parameters for the models smoothly. The lightweight and powerful algorithms, such as Decision Tree and Random Forest, are applied to train the proposed model on the updated benchmark dataset, CICIoT2023, consisting of seven attack categories, namely DDoS, DoS, Reconnaissance, Web-based, Brute Force, Spoofing, and Mirai. The results show that the model achieves superior performance with a 99.64% of F1 score. Furthermore, by reducing the feature set from 46 to 5, the model delivers a quick prediction time of 10.89 seconds. These results confirm the model’s effectiveness and efficiency, making it well-suited for deployment in IoT networks.
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) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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".