Securing Industrial Control Systems: Components, Cyber Threats, and Machine Learning-Driven Defense Strategies
Open accessThe DOI matches its Crossref record; 131 of the 131 references it cites were found in a registry or an index.
Abstract
Industrial Control Systems (ICS), which include Supervisory Control and Data Acquisition (SCADA) systems, Distributed Control Systems (DCS), and Programmable Logic Controllers (PLC), play a crucial role in managing and regulating industrial processes. However, ensuring the security of these systems is of utmost importance due to the potentially severe consequences of cyber attacks. This article presents an overview of ICS security, covering its components, protocols, industrial applications, and performance aspects. It also highlights the typical threats and vulnerabilities faced by these systems. Moreover, the article identifies key factors that influence the design decisions concerning control, communication, reliability, and redundancy properties of ICS, as these are critical in determining the security needs of the system. The article outlines existing security countermeasures, including network segmentation, access control, patch management, and security monitoring. Furthermore, the article explores the integration of machine learning techniques to enhance the cybersecurity of ICS. Machine learning offers several advantages, such as anomaly detection, threat intelligence analysis, and predictive maintenance. However, combining machine learning with other security measures is essential to establish a comprehensive defense strategy for ICS. The article also addresses the challenges associated with existing measures and provides recommendations for improving ICS security. This paper becomes a valuable reference for researchers aiming to make meaningful contributions within the constantly evolving ICS domain by providing an in-depth examination of the present state, challenges, and potential future advancements.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Figures














Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“However, direct translation of enterprise Zero Trust principles to manufacturing environments is not straightforward.Industrial Control Systems operate with different threat models, risk tolerances, and operational constraints compared to traditional IT systems [15].”
From Manufacturing Cybersecurity for SMEs: Implementing Zero Trust in Legacy Industrial Environments (2026) · cites this paper as [15]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Industrial Control Systems operate under constraints differing fundamentally from IT systems [15].”
From Manufacturing Cybersecurity for SMEs: Implementing Zero Trust in Legacy Industrial Environments (2026) · cites this paper as [15]
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
N-BaIoT—Network-Based Detection of IoT Botnet Attacks Using Deep Autoencoders
Meidan, Y., Bohadana, M., Mathov, Y., Mirsky, Y., Shabtai, A., Breitenbacher, D., & Elovici, Y. (2018) · IEEE Pervasive Computing · doi:10.1109/mprv.2018.03367731 · Cited by 1,483
Machine Learning and Deep Learning Methods for Cybersecurity
Xin, Y., Kong, L., Liu, Z., Chen, Y., Li, Y., Zhu, H., Gao, M., Hou, H., & Wang, C. (2018) · IEEE Access · doi:10.1109/access.2018.2836950 · Cited by 1,228 · cited 1×
“Machine learning has a substantial impact on cybersecurity, as it facilitates a range of techniques for the detection and mitigation of cyber threats [118].”
BackgroundA Comparative Evaluation of Unsupervised Anomaly Detection Algorithms for Multivariate Data
Goldstein, M., & Uchida, S. (2016) · PLOS ONE · doi:10.1371/journal.pone.0152173 · Cited by 1,032 · cited 1×
“…[122] Random Forest [123] NeuralNetworks [124] [125] Autoencoders [126] [127] Density-based Clustering [128] Local Outlier Factor [129] Gaussian Mixture Models [130] The above mentioned machine learning techniques for anomaly detection are powerful tools for identifying outliers…”
MethodA survey on security control and attack detection for industrial cyber-physical systems
Ding, D., Han, Q.-L., Xiang, Y., Ge, X., & Zhang, X.-M. (2018) · Neurocomputing · doi:10.1016/j.neucom.2017.10.009 · Cited by 944 · cited 1×
“This is regarded as one of the most significant threats to the machine learning process [186].”
BackgroundMachine Learning for Predictive Maintenance: A Multiple Classifier Approach
Susto, G. A., Schirru, A., Pampuri, S., McLoone, S., & Beghi, A. (2015) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2014.2349359 · Cited by 901
A Comprehensive Review on Malware Detection Approaches
Aslan, O., & Samet, R. (2020) · IEEE Access · doi:10.1109/access.2019.2963724 · Cited by 649
A Survey on Machine Learning Techniques for Cyber Security in the Last Decade
Shaukat, K., Luo, S., Varadharajan, V., Hameed, I. A., & Xu, M. (2020) · IEEE Access · doi:10.1109/access.2020.3041951 · Cited by 530 · cited 1×
“Machine Learning as a part of IDSs has had positive results by using different kinds of learning, including supervised, unsupervised, and reinforcement learning [170].”
BackgroundA Taxonomy of Cyber Attacks on SCADA Systems
Zhu, B., Joseph, A., & Sastry, S. (2011) · 2011 International Conference on Internet of Things and 4th International Conference on Cyber, Physical and Social Computing · doi:10.1109/ithings/cpscom.2011.34 · Cited by 458 · cited 1×
“Only the developers cared about the SCADA security [20].”
BackgroundSecurity of smart manufacturing systems
Tuptuk, N., & Hailes, S. (2018) · Journal of Manufacturing Systems · doi:10.1016/j.jmsy.2018.04.007 · Cited by 456
The Use of MQTT in M2M and IoT Systems: A Survey
Mishra, B., & Kertesz, A. (2020) · IEEE Access · doi:10.1109/access.2020.3035849 · Cited by 429
Finding surprising patterns in a time series database in linear time and space
Keogh, E., Lonardi, S., & Chiu, B. '.-C. (2002) · Proceedings of the eighth ACM SIGKDD international conference on Knowledge discovery and data mining · doi:10.1145/775047.775128 · Cited by 404 · cited 1×
“[144], according to research conducted on the Petroleum industry, which is one of such real-world application scenarios.”
BackgroundSajid, A., Abbas, H., & Saleem, K. (2016) · IEEE Access · doi:10.1109/access.2016.2549047 · Cited by 401
Making machine learning robust against adversarial inputs
Goodfellow, I., McDaniel, P., & Papernot, N. (2018) · Communications of the ACM · doi:10.1145/3134599 · Cited by 358 · cited 1×
“Therefore, a range of models and diverse datasets are essential to create system-wide solutions [187]; • Machine learning models impose stringent demands regarding the dimensions, con-figurations, and formats of input data: Despite the vast amounts of data that Cyber-Physical Systems (CPS) collect,…”
BackgroundCyber risk and cybersecurity: a systematic review of data availability
Cremer, F., Sheehan, B., Fortmann, M., Kia, A. N., Mullins, M., Murphy, F., & Materne, S. (2022) · The Geneva Papers on Risk and Insurance - Issues and Practice · doi:10.1057/s41288-022-00266-6 · Cited by 355 · cited 1×
“In cybersecurity, obtaining such data can be difficult due to the scarcity of certain types of cyber attack data or the potential risks associated with using real-world attack data [182].”
BackgroundRaja Santhi, A., & Muthuswamy, P. (2023) · International Journal on Interactive Design and Manufacturing (IJIDeM) · doi:10.1007/s12008-023-01217-8 · Cited by 353
A Review of Local Outlier Factor Algorithms for Outlier Detection in Big Data Streams
Alghushairy, O., Alsini, R., Soule, T., & Ma, X. (2020) · Big Data and Cognitive Computing · doi:10.3390/bdcc5010001 · Cited by 345 · cited 1×
“In ICS, LOF can identify points with significantly lower density as anomalies [164].”
BackgroundOutlier Detection: Methods, Models, and Classification
Boukerche, A., Zheng, L., & Alfandi, O. (2021) · ACM Computing Surveys · doi:10.1145/3381028 · Cited by 334
Tariq, U., Ahmed, I., Bashir, A. K., & Shaukat, K. (2023) · Sensors · doi:10.3390/s23084117 · Cited by 329 · cited 1×
“However, it also presents a challenge, as integrating Industrial Control Systems with external networks, such as the internet, expands the attack surface, making them more susceptible to cyber threats without proper security measures [4].”
BackgroundA Survey on SCADA Systems: Secure Protocols, Incidents, Threats and Tactics
Pliatsios, D., Sarigiannidis, P., Lagkas, T., & Sarigiannidis, A. G. (2020) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2020.2987688 · Cited by 320 · cited 1×
“Additionally, this architecture enhanced the performance level of SCADA by allowing several servers to run in parallel to handle several tasks [25].”
BackgroundA comprehensive survey and taxonomy of the SVM-based intrusion detection systems
Mohammadi, M., Rashid, T. A., Karim, S. H. T., Aldalwie, A. H. M., Tho, Q. T., Bidaki, M., Rahmani, A. M., & Hosseinzadeh, M. (2021) · Journal of Network and Computer Applications · doi:10.1016/j.jnca.2021.102983 · Cited by 262 · cited 1×
“Here are a few common approaches [141]: • Support Vector Machines (SVM): SVM is a widely employed supervised learning algorithm for tasks involving classification [142].”
MethodArchitecture and security of SCADA systems: A review
Yadav, G., & Paul, K. (2021) · International Journal of Critical Infrastructure Protection · doi:10.1016/j.ijcip.2021.100433 · Cited by 261
Denial of Service Attacks on Network-Based Control Systems: Impact and Mitigation
Long, M., Wu, C.-H., & Hung, J. Y. (2005) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2005.844422 · Cited by 248
Deep Q-Learning Based Reinforcement Learning Approach for Network Intrusion Detection
Alavizadeh, H., Alavizadeh, H., & Jang-Jaccard, J. (2022) · Computers · doi:10.3390/computers11030041 · Cited by 230
Industrial and Critical Infrastructure Security: Technical Analysis of Real-Life Security Incidents
Makrakis, G. M., Kolias, C., Kambourakis, G., Rieger, C. G., & Benjamin, J. (2021) · IEEE Access · doi:10.1109/access.2021.3133348 · Cited by 227 · cited 1×
“This configuration guarantees absolute physical layer security but sacrifices bidirectional communication [98]; • Establish demilitarized zones (DMZs) to configure a physical and logical subnet-work that serves as an intermediary for connected security devices, preventing direct exposure [99].”
BackgroundUpadhyay, D., Manero, J., Zaman, M., & Sampalli, S. (2021) · IEEE Transactions on Network and Service Management · doi:10.1109/tnsm.2020.3032618 · Cited by 206 · cited 1×
“…most promising features from the power grid dataset using a GBFS module, it accesses a range of machine learning techniques based on decision trees [155,156]; • Deep Learning Autoencoders: Autoencoders are neural network structures that acquire the ability to encode input data into a…”
MethodPinto, A., Herrera, L.-C., Donoso, Y., & Gutierrez, J. A. (2023) · Sensors · doi:10.3390/s23052415 · Cited by 200 · cited 1×
“(c) Intrusion Detection Systems (IDS): Machine learning, when integrated into IDSs, has yielded favorable outcomes by leveraging various learning approaches, encompassing supervised, unsupervised, and reinforcement learning [168,169].”
BackgroundCybersecurity Threats and Their Mitigation Approaches Using Machine Learning—A Review
Ahsan, M., Nygard, K. E., Gomes, R., Chowdhury, M. M., Rifat, N., & Connolly, J. F. (2022) · Journal of Cybersecurity and Privacy · doi:10.3390/jcp2030027 · Cited by 197 · cited 1×
“Applying machine learning in cybersecurity makes the malware detection process more actionable, scalable, and effective than traditional approaches, which require human intervention [116].”
BackgroundA survey of intrusion detection on industrial control systems
Hu, Y., Yang, A., Li, H., Sun, Y., & Sun, L. (2018) · International Journal of Distributed Sensor Networks · doi:10.1177/1550147718794615 · Cited by 185 · cited 1×
“(c) Intrusion Detection Systems (IDS): Machine learning, when integrated into IDSs, has yielded favorable outcomes by leveraging various learning approaches, encompassing supervised, unsupervised, and reinforcement learning [168,169].”
BackgroundUnsupervised anomaly detection with LSTM autoencoders using statistical data-filtering
Maleki, S., Maleki, S., & Jennings, N. R. (2021) · Applied Soft Computing · doi:10.1016/j.asoc.2021.107443 · Cited by 184
Anomaly Detection Based on Sensor Data in Petroleum Industry Applications
Martí, L., Sanchez-Pi, N., Molina, J., & Garcia, A. (2015) · Sensors · doi:10.3390/s150202774 · Cited by 180 · cited 1×
“To deal with this and with the lack of labeled data for training and validation of models in some scenarios [145,146], an approach describing a combination of a fast and high-quality segmentation algorithm with a one-class support vector machine for efficient anomaly detection in turbomachines was…”
MethodIntrusion Detection Systems using Supervised Machine Learning Techniques: A survey
Abdallah, E. E., Eleisah, W., & Otoom, A. F. (2022) · Procedia Computer Science · doi:10.1016/j.procs.2022.03.029 · Cited by 176 · cited 1×
“Here are a few common approaches [141]: • Support Vector Machines (SVM): SVM is a widely employed supervised learning algorithm for tasks involving classification [142].”
MethodAnomaly detection using random forest: A performance revisited
Primartha, R., & Tama, B. A. (2017) · 2017 International Conference on Data and Software Engineering (ICoDSE) · doi:10.1109/icodse.2017.8285847 · Cited by 171
Programmable Logic Controllers in the Context of Industry 4.0
Sehr, M. A., Lohstroh, M., Weber, M., Ugalde, I., Witte, M. E., Neidig, J., Höme, S., Niknami, M., & Lee, E. A. (2020) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2020.3007764 · Cited by 170 · cited 1×
“PLCs are industrial computer control systems designed to constantly monitor the status of input devices and make decisions according to a customized program in order to manage the status of output devices [32].”
BackgroundMachine Learning for Security and the Internet of Things: The Good, the Bad, and the Ugly
Liang, F., Hatcher, W. G., Liao, W., Gao, W., & Yu, W. (2019) · IEEE Access · doi:10.1109/access.2019.2948912 · Cited by 164 · cited 1×
“Use this information to prioritize security measures based on risk levels [188].”
BackgroundSCADA vulnerabilities and attacks: A review of the state‐of‐the‐art and open issues
Alanazi, M., Mahmood, A., & Chowdhury, M. J. M. (2023) · Computers & Security · doi:10.1016/j.cose.2022.103028 · Cited by 158 · cited 1×
“In contrast, PLCs are more tailored to local control applications [14];”
BackgroundAnomaly detection of industrial control systems based on transfer learning
Wang, W., Wang, Z., Zhou, Z., Deng, H., Zhao, W., Wang, C., & Guo, Y. (2021) · Tsinghua Science & Technology · doi:10.26599/tst.2020.9010041 · Cited by 155 · cited 1×
“Deep Learning has demonstrated remarkable efficacy in autonomously acquiring valuable representations of intricate data [158].”
BackgroundAnalysis of Autoencoders for Network Intrusion Detection
Song, Y., Hyun, S., & Cheong, Y.-G. (2021) · Sensors · doi:10.3390/s21134294 · Cited by 151
Design of an IoT-PLC: A containerized programmable logical controller for the industry 4.0
Mellado, J., & Núñez, F. (2021) · Journal of Industrial Information Integration · doi:10.1016/j.jii.2021.100250 · Cited by 134 · cited 1×
“A team of researchers proposed an IoT-PLC version that possesses regulatory control features, incorporates fog computing capabilities for tasks such as data filtering, field data storage, and supports various wireless interfaces that can be managed autonomously [36].”
BackgroundAnalyzing business process anomalies using autoencoders
Nolle, T., Luettgen, S., Seeliger, A., & Mühlhäuser, M. (2018) · Machine Learning · doi:10.1007/s10994-018-5702-8 · Cited by 124 · cited 1×
“SupportVectorMachines [122] Random Forest [123] NeuralNetworks [124] [125] Autoencoders [126] [127] Density-based Clustering [128] Local Outlier Factor [129] Gaussian Mixture Models [130] The above mentioned machine learning techniques for anomaly detection are powerful tools for identifying…”
MethodAnomaly-based Intrusion Detection in Industrial Data with SVM and Random Forests
Anton, S. D. D., Sinha, S., & Dieter Schotten, H. (2019) · 2019 International Conference on Software, Telecommunications and Computer Networks (SoftCOM) · doi:10.23919/softcom.2019.8903672 · Cited by 118 · cited 1×
“…of Decision Trees, binary classifiers consisting of one root node, several internal split nodes, and leaf nodes that are used to classify events [148]; • Neural Networks: Neural networks, such as feed-forward networks or recurrent neural networks (RNNs), can also be used for supervised anomaly…”
MethodAhmed, K. I., Tahir, M., Habaebi, M. H., Lau, S. L., & Ahad, A. (2021) · Sensors · doi:10.3390/s21155122 · Cited by 117 · cited 1×
“…knowledge from the environment, whether on the cloud or high-computational edge devices, without relying on a pre-established training dataset [180]; • Leveraging Machine Learning for Predictive Maintenance in ICS: A group of researchers introduced a Predictive Maintenance approach that…”
Background”A Novel MQTT Security framework In Generic IoT Model”
Patel, C., & Doshi, N. (2020) · Procedia Computer Science · doi:10.1016/j.procs.2020.04.150 · Cited by 107
SCADA Systems: Challenges for Forensic Investigators
Ahmed, I., Obermeier, S., Naedele, M., & Richard III, G. G. (2012) · Computer · doi:10.1109/mc.2012.325 · Cited by 106 · cited 1×
“Cyber attacks targeting industrial facilities result in widespread repercussions [42].”
BackgroundSengan, S., V, S., V, I., Velayutham, P., & Ravi, L. (2021) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2021.107211 · Cited by 105 · cited 1×
“SupportVectorMachines [122] Random Forest [123] NeuralNetworks [124] [125] Autoencoders [126] [127] Density-based Clustering [128] Local Outlier Factor [129] Gaussian Mixture Models [130] The above mentioned machine learning techniques for anomaly detection are powerful tools for identifying…”
MethodA Methodology for Modeling Interoperability of Smart Sensors in Smart Grids
Song, E. Y., FitzPatrick, G. J., Lee, K. B., & Griffor, E. (2021) · IEEE Transactions on Smart Grid · doi:10.1109/tsg.2021.3124490 · Cited by 99 · cited 1×
“The primary purpose of the slave or outstation is to respond to requests initiated by the master [67].”
BackgroundCyber-attacks detection in industrial systems using artificial intelligence-driven methods
Wang, W., Harrou, F., Bouyeddou, B., Senouci, S., & Sun, Y. (2022) · International Journal of Critical Infrastructure Protection · doi:10.1016/j.ijcip.2022.100542 · Cited by 95 · cited 1×
“…promising features from the power grid dataset using a GBFS module, it accesses a range of machine learning techniques based on decision trees [155,156]; • Deep Learning Autoencoders: Autoencoders are neural network structures that acquire the ability to encode input data into a…”
MethodZhu, N., Zhu, C., Zhou, L., Zhu, Y., & Zhang, X. (2022) · Applied Sciences · doi:10.3390/app122010456 · Cited by 95 · cited 1×
“Moreover, it surpasses comparable efforts within the same category [171].”
BackgroundA Deep Reinforcement Learning Approach for Anomaly Network Intrusion Detection System
Hsu, Y.-F., & Matsuoka, M. (2020) · IEEE International Conference on Cloud Networking · doi:10.1109/cloudnet51028.2020.9335796 · Cited by 89 · cited 1×
“…network intrusions and consistently improve its detection capabilities; – Deep Learning: Deep learning models, including recurrent neural networks (RNNs) and convolutional neural networks (CNNs), can be utilized in IDS to capture intricate patterns and temporal dependencies within ICS data [179].”
BackgroundReview on cyber vulnerabilities of communication protocols in industrial control systems
Xu, Y., Yang, Y., Li, T., Ju, J., & Wang, Q. (2017) · 2017 IEEE Conference on Energy Internet and Energy System Integration (EI2) · doi:10.1109/ei2.2017.8245509 · Cited by 85
Vulnerability and Impact Analysis of the IEC 61850 GOOSE Protocol in the Smart Grid
Reda, H. T., Ray, B., Peidaee, P., Anwar, A., Mahmood, A., Kalam, A., & Islam, N. (2021) · Sensors · doi:10.3390/s21041554 · Cited by 80 · cited 1×
“[86] IEC 60870-5-104 [87] IEC 61850 [88] IEC 61400-25 [89] IEEE C37.”
Security Challenges in Industry 4.0 PLC Systems
Hajda, J., Jakuszewski, R., & Ogonowski, S. (2021) · Applied Sciences · doi:10.3390/app11219785 · Cited by 78 · cited 1×
“PLCs have evolved significantly, with a version incorporating Ethernet protocol based network connectivity that enables them to share data with a variety of devices and systems such as other PCs, SCADA, and even cloud-based platforms [35].”
BackgroundAutonomous Network Defence using Reinforcement Learning
Foley, M., Hicks, C., Highnam, K., & Mavroudis, V. (2022) · ACM Asia Conference on Computer and Communications Security (ASIA CCS) · doi:10.1145/3488932.3527286 · Cited by 78 · cited 1×
“However, it might be less commonly used due to the need for careful tuning and potential risks in real-world environments [177].”
BackgroundFolgado, F. J., González, I., & Calderón, A. J. (2023) · Internet of Things · doi:10.1016/j.iot.2023.100795 · Cited by 78 · cited 1×
“Their incorporation into these paradigms is of utmost importance and have solved the earlier mentioned limitations with the below capabilities, hence resulting into robust and secure solutions for modern industrial automation, as seen below [37].”
BackgroundSverko, M., Grbac, T. G., & Mikuc, M. (2022) · IEEE Access · doi:10.1109/access.2022.3211288 · Cited by 71 · cited 1×
“SCADA is among the most widely utilized technologies in Industrial Control Systems [8].”
MethodExplainable Anomaly Detection for Industrial Control System Cybersecurity
Ha, D. T., Hoang, N. X., Hoang, N. V., Du, N. H., Huong, T. T., & Tran, K. P. (2022) · IFAC-PapersOnLine · doi:10.1016/j.ifacol.2022.09.550 · Cited by 68
Xu, Z., Kakde, D., & Chaudhuri, A. (2019) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata47090.2019.9006151 · Cited by 66 · cited 1×
“…to tune the LOF model resulted in robust predictive performance, as demonstrated in both simulation experiments and real-world data applications [165]; • One-Class Support Vector Machine (OCSVM): One-Class SVM is designed for novelty detection and can be used in ICS to learn the boundaries of…”
MethodAnomaly detection model based on gradient boosting and decision tree for IoT environments security
Douiba, M., Benkirane, S., Guezzaz, A., & Azrour, M. (2022) · Journal of Reliable Intelligent Environments · doi:10.1007/s40860-022-00184-3 · Cited by 65
Aslam, N., Khan, I. U., Alansari, A., Alrammah, M. M., Alghwairy, A., Alqahtani, R., Alqahtani, R., Almushikes, M., & Hashim, M. A. (2022) · Applied Computational Intelligence and Soft Computing · doi:10.1155/2022/1558381 · Cited by 61 · cited 1×
“SupportVectorMachines [122] Random Forest [123] NeuralNetworks [124] [125] Autoencoders [126] [127] Density-based Clustering [128] Local Outlier Factor [129] Gaussian Mixture Models [130] The above mentioned machine learning techniques for anomaly detection are powerful tools for identifying…”
MethodLin, X., Zhang, X., & Xu, X. (2019) · IEEE Transactions on Computational Biology and Bioinformatics · doi:10.1109/tcbb.2019.2931717 · Cited by 58 · cited 1×
“…the other model is trained to examine gyrometric signals collected from physical sensors within the control system [150]; • Gradient Boosting: Gradient Boosting is an ensemble learning approach that blends several weak learners, such as decision trees, to construct a robust predictive model [151].”
BackgroundMaggipinto, M., Beghi, A., & Susto, G. A. (2022) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2022.3141186 · Cited by 58 · cited 1×
“By training an autoencoder on a large dataset of normal behavior, it learns to reconstruct the normal data accurately [157].”
BackgroundImproving network security monitoring for industrial control systems
Cruz, T., Barrigas, J., Proenca, J., Graziano, A., Panzieri, S., Lev, L., & Simoes, P. (2015) · 2015 IFIP/IEEE International Symposium on Integrated Network Management (IM) · doi:10.1109/inm.2015.7140399 · Cited by 56 · cited 1×
“This makes it feasible to establish a redundant security-checking mechanism that adopts a “black box” approach when assessing the behavior of the monitored devices [108].”
BackgroundAnalysis of IEEE C37.118 and IEC 61850-90-5 synchrophasor communication frameworks
Khan, R., McLaughlin, K., Laverty, D., & Sezer, S. (2016) · IEEE Power Engineering Society General Meeting · doi:10.1109/pesgm.2016.7741343 · Cited by 53 · cited 1×
“118 [90]”
SCADA communication protocols: vulnerabilities, attacks and possible mitigations
Pidikiti, D. S., Kalluri, R., Kumar, R., & Bindhumadhava, B. S. (2013) · CSI Transactions on ICT · doi:10.1007/s40012-013-0013-5 · Cited by 52 · cited 1×
“The third-generation SCADA architecture thus facilitated greater flexibility, scalability, and accessibility, making it more adaptable to modern industrial demands [24].”
BackgroundPLC security and critical infrastructure protection
Sandaruwan, G. P. H., Ranaweera, P. S., & Oleshchuk, V. A. (2013) · IEEE International Conference on Industrial and Information Systems (ICIIS) · doi:10.1109/iciinfs.2013.6731959 · Cited by 51 · cited 1×
“While playing important roles in the ICS context, PLCs and RTUs lack adequate security mechanisms to overcome buffer overflow exploits or man-in-the-middle and a wider array of other cyber attacks [106,107].”
BackgroundYlmaz, E. N., Ciylan, B., Gonen, S., Sindiren, E., & Karacayilmaz, G. (2018) · 2018 6th International Istanbul Smart Grids and Cities Congress and Fair (ICSG) · doi:10.1109/sgcf.2018.8408947 · Cited by 51
Evaluation of Machine Learning Algorithms for Anomaly Detection in Industrial Networks
Bernieri, G., Conti, M., & Turrin, F. (2019) · IEEE International Symposium on Measurements & Networking (M&N) · doi:10.1109/iwmn.2019.8805036 · Cited by 48 · cited 1×
“(a) Supervised machine learning-based anomaly detection approaches: Supervised machine learning-based anomaly detection approaches can be applied to strengthen the cybersecurity of ICS [140].”
Artificial neural networks based techniques for anomaly detection in Apache Spark
Alnafessah, A., & Casale, G. (2019) · Cluster Computing · doi:10.1007/s10586-019-02998-y · Cited by 47
Enhanced Modbus/TCP Security Protocol: Authentication and Authorization Functions Supported
Martins, T., & Oliveira, S. V. G. (2022) · Sensors · doi:10.3390/s22208024 · Cited by 45 · cited 1×
“…of the Modbus protocol, as seen below: (a) A group of researchers proposed the Modbus/TCP Security protocol, which incorporates authentication and authorization mechanisms to ensure protection against deliberate unauthorized access as an enhancement for improved security in the ICS framework [74].”
MethodTerai, A., Abe, S., Kojima, S., Takano, Y., & Koshijima, I. (2017) · 2017 IEEE European Symposium on Security and Privacy Workshops (EuroS&PW) · doi:10.1109/eurospw.2017.62 · Cited by 42 · cited 1×
“In anomaly detection, SVM can be trained on labeled data, where normal behavior is labeled as one class and anomalies as another [143].”
MethodAttacking and Defending DNP3 ICS/SCADA Systems
Kelli, V., Grammatikis, P. I. R., Sesis, A., Λάγκας, Θ., Fountoukidis, E., Kafetzakis, E., Giannoulakis, I., & Sarigiannidis, P. G. (2022) · International Conference on Distributed Computing in Smart Systems and the Internet of Things (DCOSS-IoT) · doi:10.1109/dcoss54816.2022.00041 · Cited by 42
Securing communications for SCADA and critical industrial systems
Bartman, T., & Carson, K. (2016) · Conference for Protective Relay Engineers · doi:10.1109/cpre.2016.7914914 · Cited by 40
A Network Traffic Anomaly Detection Method Based on Gaussian Mixture Model
Yu, B., Zhang, Y., Xie, W., Zuo, W., Zhao, Y., & Wei, Y. (2023) · Electronics · doi:10.3390/electronics12061397 · Cited by 38
Research on Industrial Control Anomaly Detection Based on FCM and SVM
Shang, W., Cui, J., Song, C., Zhao, J., & Zeng, P. (2018) · IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom) · doi:10.1109/trustcom/bigdatase.2018.00042 · Cited by 37 · cited 1×
“…to the conventional intrusion detection approach, this method can notably decrease the training duration and enhance classification accuracy, all without prior knowledge of class labels [147]; • Random Forest: Random Forest is an ensemble learning technique that amal-gamates numerous decision trees.”
MethodResearch and Improvement of Isolation Forest in Detection of Local Anomaly Points
Gao, R., Zhang, T., Sun, S., & Liu, Z. (2019) · Journal of Physics Conference Series · doi:10.1088/1742-6596/1237/5/052023 · Cited by 37 · cited 1×
“SupportVectorMachines [122] Random Forest [123] NeuralNetworks [124] [125] Autoencoders [126] [127] Density-based Clustering [128] Local Outlier Factor [129] Gaussian Mixture Models [130] The above mentioned machine learning techniques for anomaly detection are powerful tools for identifying…”
MethodReal-time Industrial Communication by using OPC UA Field Level Communication
Panda, S. K., Majumder, M., Wiśniewski, Ł., & Jasperneite, J. (2020) · IEEE International Conference on Emerging Technologies and Factory Automation (ETFA) · doi:10.1109/etfa46521.2020.9211998 · Cited by 37 · cited 1×
“Open Platform Communications (OPC): OPC is a set of standards for industrial communication, and it plays a crucial role in Industry 4.0, which focuses on the automation and digitization of manufacturing processes [82].”
BackgroundInfluentialA forensics and compliance auditing framework for critical infrastructure protection
Henriques, J., Caldeira, F., Cruz, T., & Simões, P. (2023) · International Journal of Critical Infrastructure Protection · doi:10.1016/j.ijcip.2023.100613 · Cited by 37 · cited 1×
“…Management system (SIEM) to gather pertinent data from various origins, detect variances from established norms, and execute suitable responses [110]; • Establish a SIEM system to oversee, analyze, and correlate event logs throughout the ICS network for the detection of intrusion attempts [111].”
BackgroundCybersecurity of Industrial Systems
Flaus, J. (2019) · Wiley eBooks · doi:10.1002/9781119644538 · Cited by 35
Vogel‐Heuser, B., Feldmann, S., Werner, T., & Diedrich, C. (2011) · Annual Conference of the IEEE Industrial Electronics Society (IECON) · doi:10.1109/iecon.2011.6119656 · Cited by 33 · cited 1×
“The entire system’s sub-components are controlled by multiple controllers, e.g., PLC [27].”
BackgroundChallenges of Machine Learning Based Monitoring for Industrial Control System Networks
Mantere, M., Uusitalo, I., Sailio, M., & Noponen, S. (2012) · International Conference on Advanced Information Networking and Applications Workshops (WAINA) · doi:10.1109/waina.2012.135 · Cited by 33 · cited 1×
“It is important that no measuring device or monitoring system interferes with the ICS environment under scrutiny [109]; • Configure Intrusion Detection Systems (IDS) to create alarms for any ICS network traffic outside normal operations; • Track and monitor audit trails on critical areas of ICS.”
BackgroundA deep density based and self-determining clustering approach to label unknown traffic
Monshizadeh, M., Khatri, V., Kantola, R., & Yan, Z. (2022) · Journal of Network and Computer Applications · doi:10.1016/j.jnca.2022.103513 · Cited by 33 · cited 1×
“In other words, when several clustering algorithms are applied, the more two samples fall into the same cluster, the more likely they belong to the same attack type [176].”
BackgroundTackling imbalanced data in cybersecurity with transfer learning: a case with ROP payload detection
Wang, H., Singhal, A., & Liu, P. (2023) · Cybersecurity · doi:10.1186/s42400-022-00135-8 · Cited by 31 · cited 1×
“This can lead to biased models and poorer performance in detecting rare cyber threats [184]; • Adversarial Attacks: Adversaries can attempt to manipulate ML models by crafting adversarial examples, which are carefully designed inputs to cause misclassification.”
BackgroundGăitan, V. G., & Zagan, I. (2021) · Sensors · doi:10.3390/s21010246 · Cited by 30
Isolation Forest Based on Minimal Spanning Tree
Gałka, Ł., Karczmarek, P., & Tokovarov, M. (2022) · IEEE Access · doi:10.1109/access.2022.3190505 · Cited by 28 · cited 1×
“Conversely, the evaluation function focuses on navigating the analyzed element through these trees [162]; • Density-Based Clustering (like DBSCAN): Density-based clustering methods group data points based on their density.”
MethodKelli, V., Grammatikis, P. I. R., Λάγκας, Θ., Markakis, E., & Sarigiannidis, P. G. (2022) · IEEE International Conference on Cyber Security and Resilience (CSR) · doi:10.1109/csr54599.2022.9850291 · Cited by 28 · cited 1×
“[85]”
A security mechanism of Web Services-based communication for wind power plants
Liu, N., Zhang, J., & Liu, W. (2008) · doi:10.1109/pes.2008.4596199 · Cited by 27 · cited 1×
“[86] IEC 60870-5-104 [87] IEC 61850 [88] IEC 61400-25 [89] IEEE C37.”
CANF: Clustering and anomaly detection method using nearest and farthest neighbor
Faroughi, A., & Javidan, R. (2018) · Future Generation Computer Systems · doi:10.1016/j.future.2018.06.031 · Cited by 27
Current cyber security threats and challenges in critical infrastructures protection
Kozik, R., & Choraś, M. (2013) · doi:10.1109/icoia.2013.6650236 · Cited by 26 · cited 1×
“While playing important roles in the ICS context, PLCs and RTUs lack adequate security mechanisms to overcome buffer overflow exploits or man-in-the-middle and a wider array of other cyber attacks [106,107].”
BackgroundEncrypted DNP3 Traffic Classification Using Supervised Machine Learning Algorithms
de Toledo, T. R., & Torrisi, N. M. (2019) · Machine Learning and Knowledge Extraction · doi:10.3390/make1010022 · Cited by 26
Louk, M. H. L., & Tama, B. A. (2022) · Big Data and Cognitive Computing · doi:10.3390/bdcc6020041 · Cited by 26 · cited 1×
“Gradient Boosting algorithms like XGBoost or LightGBM have been successful in various anomaly detection tasks [152–154].”
Method2021 State of the Practice in Data Privacy and Security
Chauhan, P. S., & Kshetri, N. (2021) · Computer · doi:10.1109/mc.2021.3083916 · Cited by 25
Misconfiguration in Firewalls and Network Access Controls: Literature Review
Alicea, M., & Alsmadi, I. M. (2021) · Future Internet · doi:10.3390/fi13110283 · Cited by 23
A Software-Defined Security Approach for Securing Field Zones in Industrial Control Systems
Yang, J. Y., Zhou, C., Tian, Y., & Yang, S. (2019) · IEEE Access · doi:10.1109/access.2019.2924800 · Cited by 20
Testbed-based Evaluation of SIEM Tool for Cyber Kill Chain Model in Power Grid SCADA System
Singh, V. K., Callupe, S. P., & Govindarasu, M. (2019) · North American Power Symposium (NAPS) · doi:10.1109/naps46351.2019.9000344 · Cited by 19 · cited 1×
“…Management system (SIEM) to gather pertinent data from various origins, detect variances from established norms, and execute suitable responses [110]; • Establish a SIEM system to oversee, analyze, and correlate event logs throughout the ICS network for the detection of intrusion attempts…”
Density-based structural embedding for anomaly detection in dynamic networks
Bansal, M., & Sharma, D. (2022) · Neurocomputing · doi:10.1016/j.neucom.2022.05.109 · Cited by 19 · cited 1×
“SupportVectorMachines [122] Random Forest [123] NeuralNetworks [124] [125] Autoencoders [126] [127] Density-based Clustering [128] Local Outlier Factor [129] Gaussian Mixture Models [130] The above mentioned machine learning techniques for anomaly detection are powerful tools for identifying…”
MethodModbus/RS-485 Attack Detection on Communication Signals with Machine Learning
Ochiai, H., Hossain, M. D., Chirupphapa, P., Kadobayashi, Y., & Esaki, H. (2023) · IEEE Communications Magazine · doi:10.1109/mcom.002.2200553 · Cited by 19
Anomaly Detection Using Support Vector Machines for Time Series Data
Yokkampon, U., Chumkamon, S., Mowshowitz, A., Fujisawa, R., & Hayashi, E. (2021) · Journal of Robotics Networking and Artificial Life · doi:10.2991/jrnal.k.210521.010 · Cited by 18 · cited 1×
“SupportVectorMachines [122] Random Forest [123] NeuralNetworks [124] [125] Autoencoders [126] [127] Density-based Clustering [128] Local Outlier Factor [129] Gaussian Mixture Models [130] The above mentioned machine learning techniques for anomaly detection are powerful tools for identifying…”
MethodShin, D.-H., Kim, G.-Y., & Euom, I.-C. (2022) · Sensors · doi:10.3390/s22176575 · Cited by 16 · cited 1×
“OPC UA, in particular, has robust security features, including authentication, encryption, and authorization, making it suitable for secure industrial communication [83].”
BackgroundOluwasegun, A., & Jung, J.-C. (2022) · Nuclear Engineering and Design · doi:10.1016/j.nucengdes.2022.112098 · Cited by 16
Martí, L., Sánchez-Pi, N., Molina, J. M., & García, A. C. B. (2016) · Journal of Applied Logic · doi:10.1016/j.jal.2016.11.015 · Cited by 15 · cited 1×
“The correct detection of unusual events empowers the decision maker to act on the system to correctly avoid, correct, or react to the associated situations [121].”
BackgroundSmartPatch: A patch prioritization framework
Yadav, G., Gauravaram, P., Jindal, A. K., & Paul, K. (2022) · Computers in Industry · doi:10.1016/j.compind.2021.103595 · Cited by 15 · cited 1×
“…existing knowledge, insights, and previous experiences related to system dynamics to identify an efficient and exceptionally effective defensive strategy [113]; • Test all patches in off-line test environments before implementation; • Implement application whitelisting on human–machine interfaces.”
BackgroundPotluri, S., & Diedrich, C. (2019) · IEEE International Conference on Automation Science and Engineering (CASE) · doi:10.1109/coase.2019.8843140 · Cited by 14 · cited 1×
“Some researchers have devised an intrusion detection system for recognizing various injection attacks, employing deep learning algorithms like stacked autoencoders and deep belief networks that are customized for this purpose [160].”
BackgroundEntropy-Based Anomaly Detection for Gaussian Mixture Modeling
Scrucca, L. (2023) · Algorithms · doi:10.3390/a16040195 · Cited by 14 · cited 1×
“…Forest [123] NeuralNetworks [124] [125] Autoencoders [126] [127] Density-based Clustering [128] Local Outlier Factor [129] Gaussian Mixture Models [130] The above mentioned machine learning techniques for anomaly detection are powerful tools for identifying outliers and unusual patterns in data,…”
Analysis of utility communication protocol IEC 61850 for substation automation systems
Pruthvi, P., Bhuvaneswari, H. B., & Sudheendran, L. (2013) · doi:10.1049/cp.2013.2504 · Cited by 13 · cited 1×
“Within the domain of substation automation, the need for high-speed communication is imperative to meet the data transfer rates required by modern automatic control and monitoring systems (source: [76]).”
BackgroundFirewall Configuration and Path Analysis for SmartGrid Networks
Gaudet, N., Sahu, A., Goulart, A., Rogers, E. J., & Davis, K. (2020) · IEEE International Workshop Technical Committee on Communications Quality and Reliability (CQR) · doi:10.1109/cqr47547.2020.9101400 · Cited by 13 · cited 1×
“A set of rules, or access control lists (ACLs), can be established to allow or block certain packets between those networks [100]; • Utilize IP geo-blocking that enables blocking outgoing and incoming network connections based on a geographic location [101].”
BackgroundKnapp, E. D., & Langill, J. T. (2014) · Elsevier eBooks · doi:10.1016/b978-0-12-420114-9.00006-x · Cited by 12
The Modbus Protocol Vulnerability Test in Industrial Control Systems
Chang, H.-C., Lin, C., Liao, D.-J., & Koo, T.-M. (2020) · International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery (CyberC) · doi:10.1109/cyberc49757.2020.00070 · Cited by 12 · cited 1×
“[86] IEC 60870-5-104 [87] IEC 61850 [88] IEC 61400-25 [89] IEEE C37.”
Machine Learning Algorithms and Approaches used in Cybersecurity
Sudhakar, M., & Kaliyamurthie, K. P. (2022) · IEEE Global Conference for Advancement in Technology (GCAT) · doi:10.1109/gcat55367.2022.9971847 · Cited by 11 · cited 1×
“It can offer real-time detection of active threats, thereby aiding cybersecurity teams in proactively preventing security breaches [117].”
BackgroundPassive Security Monitoring for IEC-60870-5-104 based SCADA Systems
Hareesh, R., Kalluri, R., Mahendra, L., Kumar, R., & Bindhumadhava, B. S. (2020) · doi:10.20533/ijicss.9781.9083.20346.2020.0010 · Cited by 10 · cited 1×
“[86] IEC 60870-5-104 [87] IEC 61850 [88] IEC 61400-25 [89] IEEE C37.”
A Review of Cyber Security Controls from An ICS Perspective
You, Y., Lee, J., Oh, J., & Lee, K. (2018) · International Conference on Platform Technology and Service · doi:10.1109/platcon.2018.8472757 · Cited by 8 · cited 1×
“Attackers take advantage of known vulnerabilities in specific protocol implementations, using readily available pre-written attack scripts, simplifying the attack process [51].”
MethodSecurity by Design Integration Mechanisms for Industrial Control Systems
Fluchs, S., Tasten, E., Mertens, M., Horch, A., Drath, R., & Fay, A. (2022) · Annual Conference of the IEEE Industrial Electronics Society (IECON) · doi:10.1109/iecon49645.2022.9968406 · Cited by 8
A Security-Enhanced Modbus TCP Protocol and Authorized Access Mechanism
Yi, F., Zhang, L., Yang, S., & Zhao, D. (2021) · IEEE International Conference on Data Science in Cyberspace · doi:10.1109/dsc53577.2021.00016 · Cited by 7
Sánchez-Pi, N., Martí, L., Molina, J. M., et al. (2014) · Communications in computer and information science · doi:10.1007/978-3-319-07767-3_19 · Cited by 7 · cited 1×
“To deal with this and with the lack of labeled data for training and validation of models in some scenarios [145,146], an approach describing a combination of a fast and high-quality segmentation algorithm with a one-class support vector machine for efficient anomaly detection in turbomachines was…”
MethodSecuring industrial automation and control systems using application whitelisting
Obermeier, S., Schierholz, R., & Hristova, A. (2014) · doi:10.1109/etfa.2014.7005242 · Cited by 6 · cited 1×
“…that enhances security by allowing systems to run only those applications that have been explicitly approved and listed in a designated whitelist [114]; • Harden field devices, including tablets and smartphones; • Replace out-of-date software and hardware devices; • After conducting thorough…”
BackgroundA Neural-Network Driven Methodology for Anomaly Detection in Apache Spark
Alnafessah, A., & Casale, G. (2018) · International Conference on the Quality of Information and Communications Technology (QUATIC) · doi:10.1109/quatic.2018.00038 · Cited by 6 · cited 1×
“SupportVectorMachines [122] Random Forest [123] NeuralNetworks [124] [125] Autoencoders [126] [127] Density-based Clustering [128] Local Outlier Factor [129] Gaussian Mixture Models [130] The above mentioned machine learning techniques for anomaly detection are powerful tools for identifying…”
MethodAdaptive Cyber Security for Critical Infrastructure
Samanis, E., Gardiner, J., & Rashid, A. (2022) · ACM/IEEE International Conference on Cyber-Physical Systems (ICCPS) · doi:10.1109/iccps54341.2022.00043 · Cited by 6
Support vector machines and Radon's theorem
Adams, H., Farnell, E., Story, B., & Amazon, S. (2022) · Foundations of Data Science · doi:10.3934/fods.2022017 · Cited by 5
Anomaly Detection of Dust Removal System Through Gradient Boosting Decision Tree Algorithm
Yang, T., Chen, L., Wang, J., Cui, Z., & Qi, J. (2021) · International Conference on Communications, Information System and Computer Engineering (CISCE) · doi:10.1109/cisce52179.2021.9445934 · Cited by 5 · cited 1×
“Gradient Boosting algorithms like XGBoost or LightGBM have been successful in various anomaly detection tasks [152–154].”
MethodIEC 61850 Packet Generator for Testing Substation Communication
Mattos, D. P. D., Magalhães, L., Muchaluat-Saade, D. C., Z., S. A. A., Soares, L. F., Delfino, A., Uchôa, L. M., Fetnandes, N. C., Lopes, Y., Moares, I., et al. (2019) · Asia-Pacific Power and Energy Engineering Conference (APPEEC) · doi:10.1109/appeec45492.2019.8994338 · Cited by 4 · cited 1×
“The IEC 61850 standard delivers services, protocols, and a structure engineered to streamline the modeling and communication of Intelligent Electronic Devices (IEDs) and supervisory equipment in power system automation [77].”
BackgroundApplying of Recurrent Neural Networks for Industrial Processes Anomaly Detection
Alabugin, S. K., & Sokolov, A. N. (2021) · Ural Symposium on Biomedical Engineering, Radioelectronics and Information Technology (USBEREIT) · doi:10.1109/usbereit51232.2021.9455060 · Cited by 4 · cited 1×
“These models are trained using labeled data and have the capability to grasp intricate patterns and relationships within the data [149].”
BackgroundIndustrial Control System Anomaly Detection Using Convolutional Neural Network Consensus
Sinha, A., Taylor, M., Srirama, N., Manikas, T. W., Larson, E. C., & Thornton, M. A. (2021) · IEEE Conference on Control Technology and Applications (CCTA) · doi:10.1109/ccta48906.2021.9659110 · Cited by 4 · cited 1×
“…system control packets, while the other model is trained to examine gyrometric signals collected from physical sensors within the control system [150]; • Gradient Boosting: Gradient Boosting is an ensemble learning approach that blends several weak learners, such as decision trees, to construct…”
BackgroundA Deep Learning Approach for Anomaly Detection in Industrial Control Systems
Doraswamy, B., & Krishna, K. L. (2022) · International Conference on Augmented Intelligence and Sustainable Systems (ICAISS) · doi:10.1109/icaiss55157.2022.10011054 · Cited by 4 · cited 1×
“It leverages the One Hot encoder for preprocessing and the Autoencoder for feature extraction [161].”
MethodSecuring Manufacturing through Patch Management for IoT Devices
Ting, V., Chou, H.-Y., & Wang, J.-H. (2023) · IEEE International Conference on Electronic Communications, Internet of Things and Big Data (ICEIB) · doi:10.1109/iceib57887.2023.10170074 · Cited by 4 · cited 1×
“Patch management reduces cybersecurity risks and ensures production availability [112].”
BackgroundRai, P., Mishra, A., & Lal, A. (2021) · International Conference on Intelligent Technologies (CONIT) · doi:10.1109/conit51480.2021.9498555 · Cited by 3 · cited 1×
“(e) IEC 61850: It is a collection of communication norms that outline protocols for designating devices, data, and communication systems linked to the automation of electric power substations [75].”
BackgroundPyatnisky, I. A., & Sokolov, A. N. (2020) · Global Smart Industry Conference (GloSIC) · doi:10.1109/glosic50886.2020.9267864 · Cited by 2 · cited 1×
“Autoencoders excel at identifying the most challenging and nonlinear dependencies within the data, making them particularly adept at achieving high-quality anomaly detection [159].”
BackgroundAnalysing the Impact of Security Characteristics on Industrial Control Systems
Abusaq, M. J., & Zohdy, M. A. (2022) · International Conference on Advanced Computing and Communication Systems (ICACCS) · doi:10.1109/icaccs54159.2022.9785285 · Cited by 2
Anomaly detection for industrial control systems
Καπογιάννη, Ε. (2018) · Dione (University of Piraeus) · Cited by 1
Control System Design of Spacecraft Mechanical Ground Support Equipment Automatic Storage System
Yu, F. A. Y., Fu, S. B. H., Qiu, T. C. T., & Wang, F. D. Z. (2018) · IEEE International Conference on Cyber Technology in Automation, Control, and Intelligent Systems · doi:10.1109/cyber.2018.8688140 · Cited by 1 · cited 1×
“This unit comprises short-circuit protection switches at all levels, control transformers, switching power supply, and other components [38]; • Processor or CPU: This component includes a microprocessor, system memory, serial communication ports, and a LAN connection.”
BackgroundMelakhsou, A. A., Batton‐Hubert, M., & Casoetto, N. (2023) · Research Square · doi:10.21203/rs.3.rs-2378527/v2 · Cited by 1
Flaus, J. (2019) · doi:10.1002/9781119644538.ch9 · Cited by 1
Flaus, J. (2019) · doi:10.1002/9781119644538.ch5 · Cited by 1 · cited 1×
“Indeed, attackers targeting industrial control systems rely on exploiting one or more existing vulnerabilities [53].”
BackgroundImplementing Security and Access Controls
Knapp, E. D., & Langill, J. T. (2014) · Elsevier eBooks · doi:10.1016/b978-0-12-420114-9.00010-1
Research works printed but not linked: 11
- Björkman, G., Sommestad, T., Ekstedt, M., Hadeli, H., Liu, K., and Chenine, M. (2023, May 29). SCADA System Architectures. Available online: https://api.semanticscholar.org/CorpusID:109456860.
- Hemsley, K.E., and Fisher, D.R.E. (2023, May 28). History of Industrial Control System Cyber Incidents (Technical Report)|OSTI.GOV, Available online: https://www.osti.gov/servlets/purl/1505628.
- (2023, May 28). 2022 ICS/OT Cybersecurity Year in Review Report. Available online: https://hub.dragos.com/ics-cybersecurity-year-in-review-2022.
- (2023, June 12). Threat Models and Risk Assessments: Security IP. Synopsys. Available online: https://www.synopsys.com/designware-ip/technical-bulletin/using-threat-models-2017q4.html.
- Seo, M.J., Kim, T.O., and Lee, H.H. (2009, January 18–21). Implementation of web services based on IEC 61400-25 for wind power plants. Proceedings of the 2009 ICCAS-SICE, Fukuoka, Japan.
- Flaus, J.-M. (2019). Cybersecurity of Industrial Systems, Wiley. · DOI
- (2023, June 06). The Risk of Industrial Control System Programmable Logic Controller. Available online: https://ieeexplore.ieee.org/document/9359077.
- Yamanishi, K., and Takeuchi, J. (2023, July 14). Discovering Outlier Filtering Rules from Unlabeled Data: Combining a Supervised Learner with an Unsupervised Learner. Available online: https://api.semanticscholar.org/CorpusID:10897169.
- Sanchez-Pi, N., Martí, L., Molina, J.M., and Garcia, A.C.B. (2014). Communications in Computer and Information Science, Springer.
- (2023, July 13). Reliability, August 2016 a Density-Based Clustering Method for…. Available online: https://rs.ieee.org/images/files/techact/Reliability/2016-08/2016-08-a03.pdf.
- Lin, J., Dang, L., Rahouti, M., and Xiong, K. (2021). ML Attack Models: Adversarial Attacks and Data Poisoning Attacks. arXiv.
Cited by
Optimizing renewable energy systems through artificial intelligence: Review and future prospects
Ukoba, K., Olatunji, K. O., Adeoye, E., Jen, T.-C., & Madyira, D. M. (2024) · Energy & Environment · doi:10.1177/0958305x241256293 · Cited by 547
“177 The fi ndings contribute to the ongoing evolution of control systems, making power plants more ef fi cient, reliable, and adaptable to changing operational conditions.”
6G Networks and the AI Revolution—Exploring Technologies, Applications, and Emerging Challenges
Chataut, R., Nankya, M., & Akl, R. (2024) · Sensors · doi:10.3390/s24061888 · Cited by 223
“By leveraging 6G’s massive connectivity and AI’s predictive maintenance capabilities, manufacturers can optimize production processes, minimize downtime, and maximize resource efficiency [29].”
BackgroundSelf-citationZhukabayeva, T. K., Pervez, A., Mardenov, Y., Othman, М., Karabayev, N., & Ahmad, Z. (2024) · IEEE Access · doi:10.1109/access.2024.3422077 · Cited by 78
“The machine inductive learning not only helps in improving the WSN cybersecurity framework but also includes an enhanced ability for utility detection and preventing cyber threats [8], [16], [17], [18].”
BackgroundSecurity and Privacy in E-Health Systems: A Review of AI and Machine Learning Techniques
Nankya, M., Mugisa, A., Usman, Y., Upadhyay, A., & Chataut, R. (2024) · IEEE Access · doi:10.1109/access.2024.3469215 · Cited by 110
“Additionally, AI/ML-driven techniques can optimize access controls, encryption methods, and authentication mechanisms to ensure robust security measures while maintaining user privacy [23].”
BackgroundSelf-citationAslam, M. M., Tufail, A., Apong, R. A. A. H. M., De Silva, L. C., & Raza, M. T. (2024) · IEEE Access · doi:10.1109/access.2024.3394848 · Cited by 51
“A review of ML-based attack and defense strategies has been studied in [114].”
Background
Metadata
- Authors
- Nankya, M., Chataut, R., & Akl, R.
- Affiliations
- Fitchburg State University (US)
- Quinnipiac University (US)
- University of North Texas (US)
- Corresponding author
- Nankya, Mary
- Venue
- Sensors
- Publisher
- MDPI AG
- Published
- 2023-10-30
- Volume
- 23
- Issue
- 21
- Pages
- 8840
- ISSN
- 1424-8220 (ISSN-L)
- PMC
- PMC10649322
- OpenAlex
- W4388018155
- Cited by
- 114
- References
- 129
- Citations by year
- 2026: 45 · 2025: 38 · 2024: 31
- FWCI
- 2.60
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Sensors (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- University of North Texas Digital Library (University of North Texas) (submittedVersion, public-domain)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Topics
- Physical Sciences › Engineering › Control and Systems Engineering › Smart Grid Security and Resilience
- Physical Sciences › Computer Science › Computer Networks and Communications › Network Security and Intrusion Detection
- Physical Sciences › Engineering › Control and Systems Engineering › Industrial Automation and Control Systems
- Keywords
- industrial control systems, ICS security, SCADA, distributed control systems, programmable logic controller, cyber threats, vulnerability (computer security), network partitioning, access control, patch management, security monitoring, machine learning for cybersecurity, anomaly detection, threat intelligence, predictive maintenance
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.