Exploratory Machine-Learning Classification of Native Lynis Warning and Suggestion Categories in GNU/Linux: A Leakage-Aware Multi-Source Study
- 15 November 2026
- book chapter
- Published by Universidad del Centro para la Innovación y el Desarrollo (UCIDE)
- p. 207
Abstract
Security-audit outputs can support host assessment, but labels produced by an auditing tool should not be interpreted as independently validated risk estimates. This exploratory study examines whether machine-learning models can reproduce Lynis's native warning-versus-suggestion categories for control identifiers not seen during training. Twenty-nine public lynis-report.dat files yielded 1,022 raw findings; after task filtering and exact deduplication, 116 unique observations remained (102 suggestions and 14 warnings). We used a grouped 70/30 hold-out by control ID, training-only class balancing, mutual-information feature selection, and four-fold stratified group cross-validation to compare 12 base classifiers and a 12-model soft-voting ensemble. Gaussian Naive Bayes was selected from cross-validation (macro F1 0.630 ± 0.176) and achieved macro F1 0.536 and balanced accuracy 0.774 on the untouched hold-out. All four test warnings were recovered, but warning precision was 0.222. These results show that the engineered representation contains signal associated with Lynis's existing categories; they do not constitute an independent validation of security-risk prioritization, exploitability, or vulnerability severity. Larger, externally labelled and longitudinal datasets are required before operational risk-prioritization claims can be tested.Keywords
This publication has 30 references indexed in Scilit:
- Log-based anomaly detection for evolving software: An incremental deep-learning approachInformation and Software Technology, 2026
- Log anomaly detection in AIOps: A real-world implementation using Large Language ModelsSystems and Soft Computing, 2026
- A comprehensive study of machine learning techniques for log-based anomaly detectionEmpirical Software Engineering, 2025
- Log Anomaly Detection Method Based on Transformer and Temporal Convolutional NetworksIEEE Access, 2025
- Impact of log parsing on deep learning-based anomaly detectionEmpirical Software Engineering, 2024
- OneLog: towards end-to-end software log anomaly detectionAutomated Software Engineering, 2024
- A robust Wide & Deep learning framework for log-based anomaly detectionApplied Soft Computing, 2024
- Deep learning for anomaly detection in log data: A surveyMachine Learning with Applications, 2023
- AutoLog: Anomaly detection by deep autoencoding of system logsExpert Systems with Applications, 2022
- Unsupervised log message anomaly detectionICT Express, 2020