Multilayer Data-Driven Cyber-Attack Detection System for Industrial Control Systems Based on Network, System, and Process Data

Zhang, Fan; Kodituwakku, Hansaka Angel Dias Edirisinghe; Hines, J. Wesley; Coble, Jamie B.

doi:10.1109/tii.2019.2891261

Cited by 278 publications

(102 citation statements)

References 16 publications

Supporting

Mentioning

102

Contrasting

Order By: Relevance

“…The associate editor coordinating the review of this manuscript and approving it for publication was Mohammad S Khan . disturbing Information Technology (IT) systems [5]. In 2015, another cyberattack by the name of Black-Energy was used to target Ukraine's power grids, causing a massive power outage that affected about 230,000 people [6].…”

Section: Stuxnet Intended To Sabotage the System's Operation Withoutmentioning

confidence: 99%

“…Consequently, safety mechanisms, which were not designed to deal with malicious attacks, face more vulnerabilities than ever before. The majority of current existing techniques on cyber-attack detection in ICSs are based on traditional IDSs, which are mainly designed for IT security analysis [5], [17]. IDSs can be categorized as signature-based and learning-based techniques.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

An Ensemble Deep Learning-Based Cyber-Attack Detection in Industrial Control System

2020

View full text Add to dashboard Cite

The integration of communication networks and the Internet of Things (IoT) in Industrial Control Systems (ICSs) increases their vulnerability towards cyber-attacks, causing devastating outcomes. Traditional Intrusion Detection Systems (IDSs), which are mainly developed to support information technology systems, count vastly on predefined models and are trained mostly on specific cyber-attacks. Besides, most IDSs do not consider the imbalanced nature of ICS datasets, thereby suffering from low accuracy and high false-positive when being put to use. In this paper, we propose a deep learning model to construct new balanced representations of the imbalanced datasets. The new representations are fed into an ensemble deep learning attack detection model specifically designed for an ICS environment. The proposed attack detection model leverages Deep Neural Network (DNN) and Decision Tree (DT) classifiers to detect cyber-attacks from the new representations. The performance of the proposed model is evaluated based on 10-fold crossvalidation on two real ICS datasets. The results show that the proposed method outperforms conventional classifiers, including Random Forest (RF), DNN, and AdaBoost, as well as recent existing models in the literature. The proposed approach is a generalized technique, which can be implemented in existing ICS infrastructures with minimum effort. INDEX TERMS Cyber-attacks, critical infrastructure, industrial control system, integrity attack, operation technology, information technology, deep learning, neural network.

show abstract

Section: Stuxnet Intended To Sabotage the System's Operation Withoutmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

An Ensemble Deep Learning-Based Cyber-Attack Detection in Industrial Control System

2020

View full text Add to dashboard Cite

show abstract

“…They offer an edge against signature-based IDS as they can detect unknown attacks providing better security to a network. There is another type of IDS known as hybrid IDS, which combines both the above-mentioned approaches for better detection of intrusions [4]. The security of today's computer networks can be improved through an IDS.…”

Section: S Siva Priya Bipin Kumar Sahu Badal Kumar Mayank Yadavmentioning

confidence: 99%

Network Intrusion Detection System using XG Boost

Priya,

Sahu,

Kumar

et al. 2019

IJEAT

View full text Add to dashboard Cite

Internet is the most widely used commodity throughout the world. Such widescale adoption of internet has resulted in drastic developments across various facets of life. Several studies indicate a surge in cybercrimes including incidents of personal privacy thefts. Network intrusion is any illegitimate and/or unidentified activity taking place over a network. So, an effective intrusion detection system is required to be developed. Through this paper, we propose an intrusion detection system that uses XG Boost algorithm to detect intrusions. To implement this approach, KDD-99 dataset has been used for inputs. This paper demonstrates that the efficiency and accuracy of intrusion detection system deployed using XG Boost algorithm is better than contemporary algorithms.

show abstract

“…These systems work mutually dependently based on a wide variety of Industrial Internet of Things (IIoT) devices for sensing and actuation. Nowdays, IACS are facing more and more cybersecurity issues [1], [2], [3], [4]. In order to assure that the systems can run exactly as expected, it is important to guarantee the correctness of the configurations of IACS as well as the massive IIoT devices.…”

Section: Introductionmentioning

confidence: 99%

A Novel Method to Prevent Misconfigurations of Industrial Automation and Control Systems

Zhang

et al. 2021

IEEE Trans. Ind. Inf.

View full text Add to dashboard Cite

show abstract

Multilayer Data-Driven Cyber-Attack Detection System for Industrial Control Systems Based on Network, System, and Process Data

Cited by 278 publications

References 16 publications

An Ensemble Deep Learning-Based Cyber-Attack Detection in Industrial Control System

An Ensemble Deep Learning-Based Cyber-Attack Detection in Industrial Control System

Network Intrusion Detection System using XG Boost

A Novel Method to Prevent Misconfigurations of Industrial Automation and Control Systems

Contact Info

Product

Resources

About