Machine Learning Approaches to Intrusion Detection System Using BO-TPE
Bibliographic record
Abstract
Intrusion detection system (IDS) has been intensively studied in the research community.The cyber threats that are evolving rapidly have caused a major challenge for IDS to achieve a reliable detection rate.Despite the application of various machine learning approaches to improve the efficiency of IDSs, present intrusion detection approaches still struggle to reach good performance.In this paper, the Canadian Institute for Cybersecurity on Intrusion Detection Systems 2017 (CICIDS-2017) dataset was selected.To solve the multi-class imbalanced classification problem, multiple imputation by chained equations (MICE) was implemented on the dataset to deal with missing data existing in the dataset.Recursive feature elimination (RFE) method with an estimator of decision tree classifier was also implemented to reduce the number of features through computation of feature importance.The training data was resampled using synthetic minority oversampling technique with combination of the edited nearest neighbor (SMOTE-ENN) to improve the detection of minority classes.Four machine learning approaches were implemented in this research which are K-nearest neighbor, random forest, XGBoost, and LightGBM were trained and tested.The hyperparameter importance of each of the models was also analyzed using Bayesian Optimization with Tree-structured Parzen Estimator (BO-TPE) to enable more experimentation on the tuning of the hyperparameters.All four machine learning approaches achieved at least 98% for all three performance metrics which are accuracy, Matthews correlation coefficient (MCC) and area under the receiver operating characteristic curve (AUROC).
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) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 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 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".