Interpretable Random Forest-Based Intrusion Detection System for Real-Time Network Anomaly Detection
Bibliographic record
Abstract
In the face of increasing complexity and frequent changes in the profile of new forms of cyber threats, advanced and zero-day attacks are often undetectable by the traditional intrusion detection systems (IDS). This research presents a real-time, interpretable IDS based on the Random Forest algorithm, targeting the identification of anomalies in network traffic with high accuracy. The proposed model is essentially trained on an almost balanced dataset, with traffic instances classified as normal or anomalous, thereby ensuring solid generalization and low bias. Evaluation of the performance of the proposed solution with respect to various classification metrics: accuracy (99.78 percent), precision (0.998), recall (0.998), and F1-score (0.998), attests to its exceptional reliability. Furthermore, an ROC and PR curve analysis with an AUC and AP score of 1.00 signifies nearly perfect separability. In order to enhance interpretability, feature importance analysis and principal component analysis (PCA) were applied to greater visual and statistical understanding of the model's decision-making process. It presents a reliable, interpretable, and high-performance AI-based IDS for real-time applications in dynamic networks.
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) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| 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".