Machine learning methods for detecting intrusions based on network traffic analysis
Bibliographic record
Abstract
The article discusses modern machine learning methods for detecting intrusions in computer networks based on network traffic analysis. An architecture for an intelligent intrusion detection system is proposed, combining an autoencoder, a one-class support vector machine, an Isolation Forest, and Extreme Gradient Boosting (XGBoost), using a deep representation of traffic in the feature vector space. The scientific novelty lies in the integration of One-Class Neural Network with an adaptive update mechanism based on Markov decision processes (MDP), which provides automatic retraining in case of changes in traffic characteristics. The study employs procedures to reduce the dimensionality of the feature space using Principal Component Analysis (PCA), t-distributed Stochastic Neighbor Embedding (tSNE), and Uniform Manifold Approximation and Projection (UMAP). (Uniform Manifold Approximation and Projection—UMAP). Explainable Artificial Intelligence (XAI) modules are proposed using SHAP (SHapley Additive exPlanations) and LIME (Local Interpretable Model-Agnostic Explanations) methods. The developed system has been tested on the CICIDS2017 (Canadian Institute for Cybersecurity Intrusion Detection System 2017) and UNSW-NB15 (University of New South Wales Network Behavior 2015) open datasets. The results demonstrate classification accuracy of up to 97%, high interpretability, and model adaptability in detecting zero-day attacks in real-time, making it suitable for critical information infrastructures
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) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.007 |
| Science and technology studies | 0.006 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.002 | 0.001 |
| 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".