Design and Evaluation of BE-RF Framework on Multi-Dataset: A Network Intrusion Detection System Using Ensemble Learning with Random Forest
Bibliographic record
Abstract
Cyber-attacks and associated challenges have caused a relentless loss of money, data, and a tragic impact on the personal and public levels.These attacks did not spare even the most critical infrastructures of the smart grid and nuclear facilities.Consequently, this has reinforced the general trend towards searching for appropriate means and techniques to prevent, reduce, or mitigate the risk of cyber-attacks.Recently, the use of artificial intelligence in various fields has proven its effectiveness due to its ability to devise fast learning and highly accurate learning models.Therefore, in this paper, we used machinelearning techniques to learn the patterns of cyberattacks and build an accurate classification model of data flow in networks to take advantage of the intelligent machine's capabilities to identify potential attacks.We propose using the Bagging Ensemble Learning method fortified by the Random Forest (BE-RF) to build a classification model for the attack categories.The random forest algorithm generates many decision trees and then combines them to obtain the most accurate threat classifier, while the bagging ensemble improves the stability and accuracy of machine learning (ML) algorithms.We employ UNSW-NB15, NSL-KDD, and CICIDS2017 datasets for evaluating the classification performance over several previously used classifiers, such as AlexNet, Convolutional Neural Network (CNN), and Bidirectional Long Short-Term Memory network (BiLSTM).According to the F1 assessment, the proposed BE-RF model achieved results of 90.43 on the UNSW-NB15 dataset, 84.9 on the NSL-KDD dataset, and 99 on the CICIDS2017 dataset.The results show the success of the proposed methodology in terms of accuracy, precision, recall, and F1 Measure compared to previous methods.
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 | 0.002 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| 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".