# Log-based Anomaly Detection of CPS Using a Statistical Method

## TL;DR

This paper presents a statistical outlier detection approach for identifying anomalies in CPS logs, demonstrating its effectiveness in detecting real faults in an aquarium management system, despite some limitations.

## Contribution

The paper introduces a novel log-based anomaly detection method for CPS using statistical outlier detection, validated on real system logs.

## Key findings

- Detected actual faults like mutual exclusion failures
- Identified transient functionality losses and reboots
- Some false positives and unproblematic anomalies detected

## Abstract

Detecting anomalies of a cyber physical system (CPS), which is a complex system consisting of both physical and software parts, is important because a CPS often operates autonomously in an unpredictable environment. However, because of the ever-changing nature and lack of a precise model for a CPS, detecting anomalies is still a challenging task. To address this problem, we propose applying an outlier detection method to a CPS log. By using a log obtained from an actual aquarium management system, we evaluated the effectiveness of our proposed method by analyzing outliers that it detected. By investigating the outliers with the developer of the system, we confirmed that some outliers indicate actual faults in the system. For example, our method detected failures of mutual exclusion in the control system that were unknown to the developer. Our method also detected transient losses of functionalities and unexpected reboots. On the other hand, our method did not detect anomalies that were too many and similar. In addition, our method reported rare but unproblematic concurrent combinations of operations as anomalies. Thus, our approach is effective at finding anomalies, but there is still room for improvement.