Neural network based anomaly detection for SCADA systems

Reuter, Lenhard; Jung, Oliver; Magin, Julian

doi:10.1109/icin48450.2020.9059436

Cited by 14 publications

(10 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As experimental findings show that this technique can achieve a higher detection rate and a lower false-positive rate than recently developed techniques, it could be applied in actual IICS environments. Similarly, Reuter et al in [6] developed a neural network-based anomaly detection system for SCADA. The objective was to deploy a neural network-based detection of anomalies in a software-defined network (SDN) that carries SCADA traffic where the controller provides details about traffic flow for anomaly detection.…”

Section: B Intrusion Detection Systemmentioning

confidence: 99%

A Smart Network Intrusion Detection System for Cyber Security of Industrial IoT

Gunjal¹,

Patel²,

Ebrahimi³

2023

Preprint

View full text Add to dashboard Cite

<p>The industrial sector has been making use of machines and sensors having the capability to communicate with each other. This forms a network of Industrial devices which is called Industrial Internet of Things (IIoT). IIoT is an emerging trend that can generate a huge amount of data that is vulnerable to cyber-attacks. In IIoT network, data and control instructions flow through Supervisory Control and Data Acquisition (SCADA) system. A Network Intrusion Detection System (NIDS) which can monitor realtime network traffic could be deployed between SCADA and the IIoT devices to detect cyber-attacks. NIDS with Deep Learning (DL) algorithms require large dataset for which CSE-CIC-IDS2018 and UNSW-NB15 dataset is used. The paper compares a Multi-Layer Perceptron(MLP), a Fully Connected Deep Neural Network (FCNN), and Convolutional Neural Network (CNN) on CSE-CIC-IDS2018 and UNSW-NB15 with XGBoost for feature selection.</p>

show abstract

Section: B Intrusion Detection Systemmentioning

confidence: 99%

A Smart Network Intrusion Detection System for Cyber Security of Industrial IoT

Gunjal¹,

Patel²,

Ebrahimi³

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…The statuses of the monitored and controlled physical processes are presented on the HMI consoles [2]. Moreover, HMIs present a graphical display of various emergency notifications, such as alerts and warnings, which allow operators to interact with the systems [7,31]. Historians are databases that store the various data gathered by the SCADA systems.…”

Section: Brief Overview Of Modern Scada Architecturementioning

confidence: 99%

“…Supervised learning algorithms are aimed at training labelled input data for a particular output [25,37]. The algorithms are trained to detect some underlying patterns between the input dataset and the output labels, which allows them to successfully label unlabeled dataset [31]. Based on the mode of the learning task, supervised learning algorithms are basically categorized into regression and classification.…”

Section: Supervised Learning For Scada Securitymentioning

confidence: 99%

“…The authors in [44] used weighted particle based cuckoo search optimization based artificial neural network model for classifying SCADA intrusions. Reuter et al [31] proposed an artificial neural network based anomaly detection for the CSE-CIC-IDS 2017 dataset. Li et al [106] modelled a back propagation neural network for analyzing the health assessment for fault and intrusion using wind turbines SCADA dataset.…”

Section: Artificial Neural Network (Ann)mentioning

confidence: 99%

See 1 more Smart Citation

A Review of Research Works on Supervised Learning Algorithms for SCADA Intrusion Detection and Classification

et al. 2021

View full text Add to dashboard Cite

Supervisory Control and Data Acquisition (SCADA) systems play a significant role in providing remote access, monitoring and control of critical infrastructures (CIs) which includes electrical power systems, water distribution systems, nuclear power plants, etc. The growing interconnectivity, standardization of communication protocols and remote accessibility of modern SCADA systems have contributed massively to the exposure of SCADA systems and CIs to various forms of security challenges. Any form of intrusive action on the SCADA modules and communication networks can create devastating consequences on nations due to their strategic importance to CIs’ operations. Therefore, the prompt and efficient detection and classification of SCADA systems intrusions hold great importance for national CIs operational stability. Due to their well-recognized and documented efficiencies, several literature works have proposed numerous supervised learning techniques for SCADA intrusion detection and classification (IDC). This paper presents a critical review of recent studies whereby supervised learning techniques were modelled for SCADA intrusion solutions. The paper aims to contribute to the state-of-the-art, recognize critical open issues and offer ideas for future studies. The intention is to provide a research-based resource for researchers working on industrial control systems security. The analysis and comparison of different supervised learning techniques for SCADA IDC systems were critically reviewed, in terms of the methodologies, datasets and testbeds used, feature engineering and optimization mechanisms and classification procedures. Finally, we briefly summarized some suggestions and recommendations for future research works.

show abstract

“…We have applied deep neural network based algorithms, also known as Deep Learning [32]. The system consists of a classifier, an autoencoder, and a pre-and post-processing stage [33].…”

Section: Online System Integrity Controlmentioning

confidence: 99%

The Impact of Virtualisation Techniques on Power System Control Networks

et al. 2020

Self Cite

View full text Add to dashboard Cite

Virtualisation is a concept successfully applied to IT systems. In this work, we analyse how virtualisation approaches, such as edge computing, brokerage and software-defined networking, can be applied in the area of electricity grid management and control systems. Power system information and communications technology is currently subject to significant changes. Networked power grid components including renewable energy units, electric vehicles and heat pumps need to be integrated into grid management systems. We studied how virtualisation techniques can support system operators in increasing an energy and communication system’s dependability and situational awareness, and how manual (mostly field-level) configuration and engineering efforts can be reduced. Starting from a working hypothesis, three concrete use-cases were implemented and the performance enhancements were benchmarked to allow for well-informed answers to the questions above. We took a close look at application-protocol-independent redundancy, grid-based routing and online system integrity control. In these study cases, we found significant improvements could be achieved with virtualisation in terms of reduced engineering effort, better system management and simplification in high-level system architecture, since implementation details are hidden by the virtualisation approach.

show abstract

Neural network based anomaly detection for SCADA systems

Cited by 14 publications

References 21 publications

A Smart Network Intrusion Detection System for Cyber Security of Industrial IoT

A Smart Network Intrusion Detection System for Cyber Security of Industrial IoT

A Review of Research Works on Supervised Learning Algorithms for SCADA Intrusion Detection and Classification

The Impact of Virtualisation Techniques on Power System Control Networks

Contact Info

Product

Resources

About