Anomaly Detection in Industrial Control Systems Based on Cross-Domain Representation Learning
Authors:
- Dongyang ZhanDZDongyang Zhan
- Wenqi ZhangWZWenqi Zhang
- Lin YeLYLin Ye
- Xiangzhan YuXYXiangzhan Yu
- Hongli ZhangHZHongli Zhang
- Zheng HeZHZheng He
Preprint
Abstract
Industrial control systems (ICSs) are widely used in industry, and their security and stability are very important. Once the ICS is attacked, it may cause serious damage. Therefore, it is very important to detect anomalies in ICSs. ICS can monitor and manage physical devices remotely using communication networks. The existing anomaly detection approaches mainly focus on analyzing the security of network traffic or sensor data. However, the behaviors of different domains (e.g., network traffic and sensor physical status) of ICSs are correlated, so it is difficult to comprehensively identify anomalies by analyzing only a single domain. In this paper, an anomaly detection approach based on cross-domain representation learning in ICSs is proposed, which can learn the joint features of multi-domain behaviors and detect anomalies within different domains. After constructing a cross-domain graph that can represent the behaviors of multiple domains in ICSs, our approach can learn the joint features of them by leveraging graph neural networks. Since anomalies behave differently in different domains, we leverage a multi-task learning approach to identify anomalies in different domains separately and perform joint training. The experimental results show that the performance of our approach is better than existing approaches for identifying anomalies in ICSs.Keywords
All Related Versions
This publication has 20 references indexed in Scilit:
- DTAAD: Dual Tcn-attention networks for anomaly detection in multivariate time series dataKnowledge-Based Systems, 2024
- Dependable federated learning for IoT intrusion detection against poisoning attacksComputers & Security, 2023
- Global-local integration for GNN-based anomalous device state detection in industrial control systemsExpert Systems with Applications, 2022
- A two-stage fault diagnosis methodology for rotating machinery combining optimized support vector data description and optimized support vector machineMeasurement, 2022
- The effect of the Colonial Pipeline shutdown on gasoline pricesEconomics Letters, 2021
- Designing online network intrusion detection using deep auto-encoder Q-learningComputers and Electrical Engineering, 2019
- Intrusion detection system: A comprehensive reviewJournal of Network and Computer Applications, 2013
- Multiple-gradient descent algorithm (MGDA) for multiobjective optimizationComptes Rendus Mathématique, 2012
- Fault Detection and Diagnosis in Industrial Systems2001
- A plant-wide industrial process control problemComputers & Chemical Engineering, 1993