Multi-Layer Anomaly Detection Framework for Industrial Control Systems: A Comprehensive Comparative Analysis of Unsupervised Machine Learning Algorithms
Abstract
This is a preprint version of a manuscript intended for submission to a peer-reviewed journal.This version has not undergone peer review. The paper presents a comprehensive multi-layer anomaly detection framework for IndustrialControl Systems (ICS), evaluating unsupervised machine learning algorithms across IoT/OT,Linux, Windows, and network layers under realistic false positive rate constraints.
Fields of Study & Subjects
Network Security and Intrusion Detection
Anomaly Detection Techniques and Applications
Software System Performance and Reliability
Publication details
- Journal / source
- Zenodo (CERN European Organization for Nuclear Research)
- Publication date
- 15 January 2026
- Language
- EN
- Document type
- Preprint