4.6 Article

A Machine Learning Approach for Anomaly Detection in Industrial Control Systems Based on Measurement Data

期刊

ELECTRONICS
卷 10, 期 4, 页码 -

出版社

MDPI
DOI: 10.3390/electronics10040407

关键词

machine learning; industrial control systems; anomaly detection; fault detection; intrusion detection system

资金

  1. Tennessee Technological University
  2. National Science Foundation [CNS-1919855]

向作者/读者索取更多资源

The study proposed a novel solution called MIDS based on measurement data in the SCADA system, to detect abnormal activities in industrial control systems effectively even if attackers try to conceal them in the system's control layer. The supervised machine learning model, tested on a HIL testbed with various machine learning algorithms, demonstrated that random forest performed better in detecting anomalies.
Attack detection problems in industrial control systems (ICSs) are commonly known as a network traffic monitoring scheme for detecting abnormal activities. However, a network-based intrusion detection system can be deceived by attackers that imitate the system's normal activity. In this work, we proposed a novel solution to this problem based on measurement data in the supervisory control and data acquisition (SCADA) system. The proposed approach is called measurement intrusion detection system (MIDS), which enables the system to detect any abnormal activity in the system even if the attacker tries to conceal it in the system's control layer. A supervised machine learning model is generated to classify normal and abnormal activities in an ICS to evaluate the MIDS performance. A hardware-in-the-loop (HIL) testbed is developed to simulate the power generation units and exploit the attack dataset. In the proposed approach, we applied several machine learning models on the dataset, which show remarkable performances in detecting the dataset's anomalies, especially stealthy attacks. The results show that the random forest is performing better than other classifier algorithms in detecting anomalies based on measured data in the testbed.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.6
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据