SIEM+: Harnessing Machine Learning for Advanced AnomalyDetection in Cybersecurity Software
Bibliographic record
Abstract
Security Information and Event Management (SIEM) solutions are a class of software that aims to aid individuals and businesses in protecting their networks. They ingest and monitor data in real time and store essential data for future retrieval. Typical production SIEMs ingest billions of logs daily, and monitoring this data manually is not feasible. Cybersecurity software has made significant advancements in capability over the past decade. However, it is now more important than ever to adopt machine learning to aid cybersecurity experts in their daily efforts to keep up with recent surges in Internet traffic and cyber crimes. This paper introduces SIEM+, a novel framework that leverages machine learning to automatically detect anomalies in SIEM software, and was developed using an analyst-in-the-loop approach and proprietary real-world data. Our experimental results show strong performance across 8 datasets derived from proprietary real-world production data, with an average F1 score of 87.24\%. As a result of this research and an ongoing collaboration, a prototype implementation of this framework has been deployed into a production SIEM environment, and is currently used daily to reduce cybersecurity analyst workload.
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 | 0.003 | 0.006 |
| 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 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.002 |
| 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".