A stacked deep learning approach to cyber-attacks detection in industrial systems: application to power system and gas pipeline systems

Abstract

Presently, Supervisory Control and Data Acquisition (SCADA) systems are broadly adopted in remote monitoring large-scale production systems and modern power grids. However, SCADA systems are continuously exposed to various heterogeneous cyberattacks, making the detection task using the conventional intrusion detection systems (IDSs) very challenging. Furthermore, conventional security solutions, such as firewalls, and antivirus software, are not appropriate for fully protecting SCADA systems because they have distinct specifications. Thus, accurately detecting cyber-attacks in critical SCADA systems is undoubtedly indispensable to enhance their resilience, ensure safe operations, and avoid costly maintenance. The overarching goal of this paper is to detect malicious intrusions that already detoured traditional IDS and firewalls. In this paper, a stacked deep learning method is introduced to identify malicious attacks targeting SCADA systems. Specifically, we investigate the feasibility of a deep learning approach for intrusion detection in SCADA systems. Real data sets from two laboratory-scale SCADA systems, a two-line three-bus power transmission system and a gas pipeline are used to evaluate the proposed method’s performance. The results of this investigation show the satisfying detection performance of the proposed stacked deep learning approach. This study also showed that the proposed approach outperformed the standalone deep learning models and the state-of-the-art algorithms, including Nearest neighbor, Random forests, Naive Bayes, Adaboost, Support Vector Machine, and oneR. Besides detecting the malicious attacks, we also investigate the feature importance of the cyber-attacks detection process using the Random Forest procedure, which helps design more parsimonious models.

Network Intrusion Detection Method Based on Multi-Scale CNN in Internet of Things

“…In order to test the overall detection performance of intrusion data, this paper takes the KDD99 data set as the benchmark method, uses reference [22,25] as the comparison method, and runs in the same experimental environment as the M-CNN detection method to verify the optimal performance of the proposed method.…”

“…Reference [22] proposed an intrusion detection system based on deep learning for the multi-cloud Internet of things environment, and the feasibility of the method was verified based on the NSL-KDD data set; Reference [23] determined the network security level, constructed a security intrusion detection system based on real-time sequence and extreme learning machine model, and analyzed the state of the Internet of things network. Based on the security interoperability requirements of the Internet of things, reference [24] built a distributed intrusion detection model based on the bidirectional long and short-term memory model to realize the network protection of the Internet of things for smart contracts; Reference [25] adopted the stacking depth learning method to analyze and determine the network state of the SCADA system in the power network. Reference [26] proposed a new unsupervised dimensionality reduction method to detect network attacks.…”

“…e data used to support the findings of this study are included in this article. Method Accuracy (%) e proposed method 93.87 Reference [22] 92.18 Reference [25] 91.09…”

A Novel Cyber-attack Leads Prediction System using Cascaded R2CNN Model

“…Wang et al, [15] Apart from firewall security, conventional security systems are required for Supervisory control and Data acquisition (SCADA) is discussed in which deep learning approach is evaluated. It detects the malicious attacks in the SCADA environment and investigates the protection criteria of cyber-attacks detection process.…”

Intrusion Detection Model for Industrial Internet of Things Based on Improved Autoencoder

“…Deep network can not only obtain the maximum reward from the high-dimensional and massive network data environment but also have the exploration function and automatically mine more valuable information in the network environment [ 14 – 16 ]. Therefore, many scholars have carried out research studies and analyses using deep learning network.…”