Confusion Matrix Explainability to Improve Model Performance: Application to Network Intrusion Detection
Bibliographic record
Abstract
High-performance Machine Learning (ML) models are indispensable in cybersecurity due to the need for real-time threat detection, scalability in handling large datasets, and the ability to recognize complex patterns and evolving threats. These models should reduce false positives and negatives, adapt to dynamic environments, and enable automated response mechanisms. This paper introduces an innovative methodology aimed at improving the performance and interpretability of ML models in binary classification, with a distinct emphasis on network intrusion detection. The proposed approach centers on an in-depth analysis of the confusion matrix, utilizing its insights to enhance model performance. We test our methodology on the UNSW-NB15 network intrusion dataset. We managed to improve almost all metrics with an increase in accuracy from 81.92% to 89.6%, recall from 76.42% to 89.22%, and F1 score from 82.51% to 89.76%, with the potential to obtain more improvements.
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 | 0.010 | 0.056 |
| Meta-epidemiology (narrow) | 0.003 | 0.000 |
| Meta-epidemiology (broad) | 0.002 | 0.002 |
| Bibliometrics | 0.006 | 0.003 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.003 | 0.003 |
| Open science | 0.002 | 0.003 |
| Research integrity | 0.001 | 0.003 |
| Insufficient payload (model declined to judge) | 0.003 | 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".