Implementation of Isolation Forest-Based Machine Learning in Batch Anomaly Detection on Zeek Log Data (Case Study: Langkat Regency Communication and Information Agency)
Bibliographic record
Abstract
The high escalation of cyber threats against government institutions requires an adaptive and intelligent digital security system. The Langkat Regency Communication and Information Agency faces challenges in analyzing large volumes of network log data to effectively detect suspicious activity. This study aims to implement the Isolation Forest machine learning algorithm to detect anomalies in batches on Zeek log data, and classify detected anomalies into threat levels to facilitate security audits. Using the CRISP-DM framework, this study analyzed 12.1 million lines of Zeek conn.log data from December 2024 through the stages of data preparation, unsupervised modeling with Isolation Forest, and manual threshold determination for classification. The effectiveness of the model is evaluated using Precision, Recall, and F1-Score metrics against proxy labels, and the results are enriched with rule-based labeling to determine threat levels. The results of the study show that the model successfully identified 15.34% of connections as anomalies, with the dominant pattern categorized as a “High” threat detected in DNS and unknown services, indicating potential malicious activity. Quantitative evaluation yielded a precision of 0.41 and a recall of 0.08, highlighting the model's ability to detect more subtle anomalies beyond simple rules. Thus, the implementation of Isolation Forest proved effective in identifying diverse network anomaly patterns, where its combination with rule-based labeling provides functional threat context for cybersecurity teams.
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 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| 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".