Cross-Domain Industrial Intrusion Detection Deep Model Trained With Imbalanced Data
- 26 August 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 10 (1) , 584-596
Abstract
Constrained by the high acquisition and labeling cost, traffic data in industrial control systems (ICSs) are usually extremely imbalanced. Deep-learning-based (DL) industrial control intrusion detection systems (IDSs) are not applicable to dynamic networks and show a limited detection performance. In this article, we enhanced the information transmission link in adversarial domain adaptation (DA) and proposed an information-enhanced adversarial DA (IADA) method. Our method could train a cross-domain industrial intrusion detection deep model with imbalanced data and maintained high detection accuracy. The experimental results based on SCADA network layer data showed that the detection accuracy of the gated recurrent unit model trained in IADA reached 93.7% and 91.3% in the two transfer tasks with a significant cross-domain discrepancy.Keywords
Funding Information
- National Key Research and Development Program of China (2018YFB0803402)
- Natural Science Foundation of Shanxi Province (20210302124395, 20210302123131)
- Shanxi Provincial Key Research and Development Project (201903D121121)
This publication has 31 references indexed in Scilit:
- Feature-based transfer learning for network security2017
- Multi-level Anomaly Detection in Industrial Control Systems via Package Signatures and LSTM Networks2017
- Deep learning approach for Network Intrusion Detection in Software Defined Networking2016
- Auto-encoder based dimensionality reductionNeurocomputing, 2016
- A survey of intrusion detection techniques for cyber-physical systemsACM Computing Surveys, 2014
- Industrial Control System Traffic Data Sets for Intrusion Detection Research2014
- An Evaluation of Machine Learning Methods to Detect Malicious SCADA Communications2013
- A Framework for Improving the Accuracy of Unsupervised Intrusion Detection for SCADA Systems2013
- Intrusion Detection System Based on SVM for WLANProcedia Technology, 2012
- Domain Adaptation via Transfer Component AnalysisIEEE Transactions on Neural Networks, 2010