NETWORK TRAFFIC ANOMALIES DETECTION USING AN ENSEMBLE OF CLASSIFIERS
Bibliographic record
Abstract
Network technologies have been steadily developing and their application has been expanding. One of the aspects of the development is a modification of the current network attacks and the appearance of new ones. The anomalies that can be detected in network traffic conform with such attacks. Development of new and improvement of the current approaches to detect anomalies in network traffic have become an urgent task. The article suggests a hybrid approach to detect anomalies on the basis of the combined signature approach and computationally effective classifiers of machine learning: logistic regression, stochastic gradient descent and decision tree with accuracy increase due to weighted voting. The choice of the classifiers is explained by the admissible complexity of the algorithms that allows detection of network traffic events for the time close to real. Signature analysis is carried out with the help of the Zeek IDS (Intrusion Detection System) signature base. Learning is fulfilled by preliminary prepared (by excluding extra recordings and parameters) CICIDS2017 (Canadian Institute for Cybersecurity Intrusion Detection System) signature set by cross validation. The set is roughly divided into ten parts that allows us to increase the accuracy. Experimental evaluation of the developed approach comparing with individual classifiers and with other approaches by such criteria as part of type I and II errors, accuracy and level of detection, has proved the approach suitable to be applied in network attacks detection systems. It is possible to introduce the developed approach into both existing and new anomaly detection systems.
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 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.002 | 0.001 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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".