Cyberattack Detection Systems in Industrial Internet of Things (IIoT) Networks in Big Data Environments
Open accessThe DOI matches its Crossref record; 44 of the 44 references it cites were found in a registry or an index.
Abstract
The rapid expansion of the Industrial Internet of Things (IIoT) has revolutionized industrial automation and introduced significant cybersecurity challenges, particularly for supervisory control and data acquisition (SCADA) systems. Traditional intrusion detection systems (IDSs) often struggle to effectively identify and mitigate complex cyberthreats, such as denial-of-service (DoS) and distributed denial-of-service (DDoS) attacks. This study proposes an advanced IDS framework integrating machine learning, deep learning, and hybrid models to enhance cybersecurity in IIoT environments. Using the WUSTL-IIoT-2021 dataset, multiple classification models—including decision tree, random forest, multilayer perceptron (MLP), convolutional neural networks (CNNs), and hybrid deep learning architectures—were systematically evaluated based on key performance metrics, including accuracy, precision, recall, and F1 score. This research introduces several key innovations. First, it presents a comparative analysis of machine learning, deep learning, and hybrid models within a unified experimental framework, offering a comprehensive evaluation of various approaches. Second, while existing studies frequently favor hybrid models, findings from this study reveal that the standalone MLP model outperforms other architectures, achieving the highest detection accuracy of 99.99%. This outcome highlights the critical role of dataset-specific feature distributions in determining model effectiveness and calls for a more nuanced approach when selecting detection models for IIoT cybersecurity applications. Additionally, the study explores a broad range of hyperparameter configurations, optimizing model effectiveness for IIoT-specific intrusion detection. These contributions provide valuable insights for developing more efficient and adaptable IDS solutions in IIoT networks.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
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?
In the citing paper
“The global population of Internet of Things (IoT) endpoints is projected to exceed 30 billion devices by 2026”
From Agentic AI and Large Language Models for Autonomous IoT Cybersecurity: A Systematic Survey, Taxonomy, and Research Roadmap (2026) · cites this paper as [3]
In the citing paper
“detectors that achieve >99% accuracy on a single dataset routinely lose 10-20 percentage points when transferred cross-dataset”
From Agentic AI and Large Language Models for Autonomous IoT Cybersecurity: A Systematic Survey, Taxonomy, and Research Roadmap (2026) · cites this paper as [3]
Citations
Cites
A systematic analysis of performance measures for classification tasks
Sokolova, M., & Lapalme, G. (2009) · Information Processing & Management · doi:10.1016/j.ipm.2009.03.002 · Cited by 7,515 · cited 1×
“These metrics serve as standard benchmarks for assessing and comparing the effectiveness of different classification algorithms and are widely utilized in various machine learning and deep learning applications [45,46].”
Alsaedi, A., Moustafa, N., Tari, Z., Mahmood, A., & Anwar, A. (2020) · IEEE Access · doi:10.1109/access.2020.3022862 · Cited by 892 · cited 1×
“In addition, since IIoT systems usually operate over cloud-based infrastructures, cloud computing systems also become a target for attackers [27,28].”
A Comprehensive Survey on Attacks, Security Issues and Blockchain Solutions for IoT and IIoT
Sengupta, J., Ruj, S., & Das Bit, S. (2020) · Journal of Network and Computer Applications · doi:10.1016/j.jnca.2019.102481 · Cited by 844 · cited 1×
“This study employed the WUSTL-IIoT-2021 dataset to detect cyberthreats in IIoT systems, providing a robust platform for evaluating security mechanisms by simulating real-world industrial conditions [21].”
Imbalanced Learning: Foundations, Algorithms, and Applications
(2013) · Wiley eBooks · doi:10.1002/9781118646106 · Cited by 831
Machine Learning-Based Network Vulnerability Analysis of Industrial Internet of Things
Zolanvari, M., Teixeira, M. A., Gupta, L., Khan, K. M., & Jain, R. (2019) · IEEE Internet of Things Journal · doi:10.1109/jiot.2019.2912022 · Cited by 525 · cited 1×
“Additionally, digital forensic incident response (DFIR) strategies are essential for protecting supervisory control and data acquisition (SCADA) systems from cyberthreats [7].”
Tange, K., De Donno, M., Fafoutis, X., & Dragoni, N. (2020) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2020.3011208 · Cited by 410 · cited 1×
“To mitigate these risks, intrusion detection systems (IDSs) are critical in identifying anomalous network traffic, enabling proactive security measures [6].”
Sajid, A., Abbas, H., & Saleem, K. (2016) · IEEE Access · doi:10.1109/access.2016.2549047 · Cited by 401 · cited 1×
“Although integrating SCADA systems with IoT and cloud infrastructures provides cost-effectiveness and enhanced performance, it simultaneously introduces heightened cybersecurity risks, mainly due to the potential for remote access vulnerabilities [4].”
A 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×
“As machine learning continues to demonstrate significant promise in cybersecurity, research in this area has expanded rapidly [22,23] In this study, SCADA network traffic was analyzed using five machine learning models (CART, decision tree, logistic regression, naïve Bayes, random forest), five…”
Multi-Step Short-Term Power Consumption Forecasting with a Hybrid Deep Learning Strategy
Yan, K., Wang, X., Du, Y., Jin, N., Huang, H., & Zhou, H. (2018) · Energies · doi:10.3390/en11113089 · Cited by 188 · cited 1×
“Such methodologies leverage the strengths of distinct algorithms to address the shortcomings found in their isolated use [13].”
A deep learning approach for intrusion detection in Internet of Things using focal loss function
Dina, A. S., Siddique, A. B., & Manivannan, D. (2023) · Internet of Things · doi:10.1016/j.iot.2023.100699 · Cited by 159 · cited 1×
“Similarly, Dina et al. (2023) [36] proposed a deep learning-based intrusion detection model utilizing feedforward neural networks (FNNs) and convolutional neural networks (CNNs).”
Cited by
CST-AFNet: A dual attention-based deep learning framework for intrusion detection in IoT networks
Ishtiaq, W., Zannat, A., Parvez, A. H. M. S., Hossain, M. A., Kanchan, M. H., & Tarek, M. M. (2025) · Array · doi:10.1016/j.array.2025.100501 · Cited by 33
“…classical ML models such as Decision Trees, SVMs, and K-Nearest Neighbors demonstrated moderate success on legacy datasets like KDD99 and NSL-KDD, but failed to generalize to modern, real-time IIoT environments due to their limited scalability and dependence on manual feature engineering [18 – 20].”
Alblehai, F. (2025) · Scientific Reports · doi:10.1038/s41598-025-98056-2 · Cited by 22
“Orman 31 proposes an IDS framework integrating Multi-layer Perceptron (MLP), ML, DL, Random Forest (RF), and hybrid models.”
Berríos, S., Garcia, S. T., Hermosilla, P., & Allende, H. (2025) · Applied Sciences · doi:10.3390/app15116012 · Cited by 18
“This finding is in line with recent published works [15], which highlighted the higher accuracy and lower computational demand of tree-based methods in industrial cybersecurity contexts.”
InfluentialKhan, F. M., Zeb, A., RAHMAN, T., Al-Khasawneh, M. A., Daradkeh, Y. I., Siddiqui, I. F., Bashir, A. K., & Ullah, I. (2026) · Cognitive Computation · doi:10.1007/s12559-026-10559-w · Cited by 24
“IoT systems become more interlinked with essen - tial sectors, including healthcare and manufacturing [161]. effectively.”
Multi-Domain Cyber Threat Classification Using Enhanced Genetic Algorithm and Deep Neural Networks
Rana Veer Samara Sihman Bharattej, R., John, Y. M. M., G, M. B. B., Karim, B., & Saritha, G. (2025) · International Conference on Networks, Multimedia and Information Technology (NMITCON) · doi:10.1109/nmitcon65824.2025.11187556 · Cited by 7
A review of artificial intelligence-based intrusion detection in industrial internet of things
Sanjalawe, Y. K., Fraihat, S., Al-E’mari, S., & Makhadmeh, S. N. (2026) · Discover Internet of Things · doi:10.1007/s43926-026-00285-y · Cited by 21
Ahmed, A. S. F., & Abdullah, T. A. A. (2026) · Technologies · doi:10.3390/technologies14050274 · Cited by 5
Govindarajan, V., Ahmed, F., Faheem, Z. B., Bilal, M., Ayadi, M. F., & Ali, J. (2026) · ACM Transactions on Autonomous and Adaptive Systems · doi:10.1145/3787224 · Cited by 4
Nageshwaran, V., & Ezekiel, S. (2026) · doi:10.20944/preprints202606.0142.v1 · Cited by 4
ASTRID-Net: SE-enhanced triple attention deep learning framework for IoT and IIoT security
Zannat, A., Ahmmed, M. S., Hossain, M. A., Islam, M. S., & Manarat, A. S. (2026) · Scientific Reports · doi:10.1038/s41598-026-36731-8 · Cited by 3
“However, these approaches are less effective to analysis the modern threat and intrusion detection in real-time IIoT scenarios due to their reliance on handcrafted feature engineering and limited ability to adapt to evolving network behaviors 2,13,14 .”
Nageshwaran, V., & Ezekiel, S. (2026) · Electronics · doi:10.3390/electronics15122740 · Cited by 4
Al-Shibly, I., Burgas, L., & Massana, J. (2026) · Frontiers in Big Data · doi:10.3389/fdata.2026.1813265 · Cited by 2
“…Detection Systems (IDS) designed for the IIoT environment should be able to effectively represent the relationships between features and identify the temporal patterns of the attacks in the most computationally efficient way possible for deployment at the edge or near the edge devices (Orman, 2025).”
Albarrak, A. M., Ghaleb, F. A. A., Qasem, S. N., & Saeed, F. (2026) · Sensors · doi:10.3390/s26165110 · Cited by 2
“Orman [40] proposes an IDS framework integrating machine learning, deep learning, and hybrid models for https://doi.org/10.3390/s26165110 cyberattack detection in IIoT SCADA environments, evaluating architectures including decision trees, random forests, CNNs, and MLP on the WUSTL-IIoT-2021 dataset.”
InfluentialMaulida, M. F., Kurniawan, M. T., & Fathinuddin, M. (2025) · International Conference on Data Science and Its Applications (ICoDSA) · doi:10.1109/icodsa67155.2025.11157626 · Cited by 1
“The growing dependence on internet-based services in modern society has significantly heightened the vulnerability of network infrastructures to a wide range of cyberattacks [1].”
SAINT-IIOT: Elk herd optimized deep learning model for efficient anomaly detection in the IIoT
Mahalakshmi, K., & Jaison, B. (2025) · Ain Shams Engineering Journal · doi:10.1016/j.asej.2025.103625 · Cited by 1
Explainable deep learning with CNN-LSTM and LIME for securing IIoT ecosystems
Mishra, S., Almutairi, E. A., & Alshenaifi, R. (2026) · PeerJ Computer Science · doi:10.7717/peerj-cs.3454 · Cited by 1
Horák, T., Ružarovský, R., Zelník, R., Csekei, M., & Šido, J. (2026) · Machines · doi:10.3390/machines14030258 · Cited by 2
AI-Based Intrusion Detection Systems Using Deep Learning and Network Traffic Analysis
Gurram, N. T. (2025) · OITS International Conference on Information Technology (OCIT) · doi:10.1109/ocit66168.2025.11400454 · Cited by 1
From BIM to Agentic AI: predictive management systems and phygital digital twins for built heritage
Fanzini, D., Casoni, G., & Cocinis, A. D. (2026) · VITRUVIO - International Journal of Architectural Technology and Sustainability · doi:10.4995/vitruvio-ijats.2026.24846 · Cited by 1
Moucharraf, M., Ridouani, M., Salahdine, F., & Kaabouch, N. (2026) · Future Internet · doi:10.3390/fi18050266 · Cited by 1
A survey of intrusion detection datasets for communication networks
Ashraf, W., & Masoodi, F. S. (2026) · Discover Computing · doi:10.1007/s10791-026-10486-2 · Cited by 2
Enhancing IIoT security: a hybrid AI framework for intrusion detection powered by Gen-X AI
Eddine, A. D., Ghazli, A., & Bouache, M. (2025) · International Journal of Computers and Applications · doi:10.1080/1206212x.2025.2531033 · Cited by 4
Debnath, S., Bhise, Y. D., Gottam, J. R., Chikop, S. A., Sankaran, M., & Jooluri, N. (2025) · International Conference on Innovations in Intelligent Systems: Advancements in Computing, Communication, and Cybersecurity (ISAC3) · doi:10.1109/isac364032.2025.11156819
“Orman [18] proposed a state-of-the-art IDS architecture for IIoT combining ML, deep learning, and hybrid models, evaluated on the WUSTL-IIoT-2021 dataset using decision trees, random forests, MLPs, CNNs, and hybrid architectures.”
Bansal, K., & Singhrova, A. (2025) · International Conference on Intelligent Systems for Cybersecurity (ISCS) · doi:10.1109/iscs69371.2025.11386351
“Moreover, most of them are constrained by testing based on a single dataset [23, 25, 30] and are not tested on adversarial attacks or real-time data streams, which casts doubt on their operational preparedness and their generalizability despite their excellent benchmark performance.”
Soanpet, K. K. K., Kumar, R., & Kumar, R. (2025) · International Conference on Recent Trends in Electrical, Electronics and Computing Technologies (ICRTEECT) · doi:10.1109/icrteect67512.2025.11448780
Deep Learning-Based Purechain-Backed Robust Intrusion Detection System for Industrial IoT
Sumona, M. I., Tuli, E. A., Somrat, M. M. H., Kim, D., & Lee, J. (2026) · International Conference on Artificial Intelligence in Information and Communication (ICAIIC) · doi:10.1109/icaiic68212.2026.11454183
“High inference latency also undermines their effectiveness in environments requiring sub-second response times [1].”
InfluentialAdversarial Model-Based FL System for Cyberattack in IIoT System
Natrayan, L. (2026) · International Conference on Communication, Computing and Emerging Technologies (IC3ET) · doi:10.1109/ic3et64989.2026.11467159
“In [17], a hybrid approach using deep learning techniques for security purposes is tested on the IIoT dataset to provide an improvement in the safety of the system in data sharing using the anomaly detection systems.”
Prasad, G. T. S., & Sri, P. S. G. A. (2026) · OPSEARCH · doi:10.1007/s12597-026-01168-0
Khandaker, N., Keya, A. J., & Nur, F. N. (2025) · International Conference on Computer and Information Technology (ICCIT) · doi:10.1109/iccit68739.2025.11490230
“DT [14] 96.25 RF [15] 99.97 MLP [16] 99.99 Transformer-GAN-AE [11] 97.86 BERT [11] 91.36 CNN [11] 83.19 Federated (CNN+BiLSTM) [3] 93.8 Proposed 96.85 To further situate our contribution within the broader research landscape, we extended our comparison with recent state-of-the-art IDS approaches…”
InfluentialA causal and counterfactual deep learning framework for robust intrusion detection in IoT networks
Ibrahim, F. A. (2026) · AEU - International Journal of Electronics and Communications · doi:10.1016/j.aeue.2026.156407
A lightweight CNN Model for Detecting Industrial Internet of Things (IIoT) Cyber-attacks
Turki, D., Muidh, H., Mohammed, S., Fayhan, M., Ismaiel, W., & Dawood, O. S. (2026) · International Conference on Artificial Intelligence, Systems, and Emerging Technologies (ICAISET) · doi:10.1109/icaiset66439.2026.11541445
“Furthermore, paper [29] confirmed that PCA improved the Internet of Things sequencing system by increasing detection accuracy and reducing model training time.”
Alowaidi, A. E. A., & Cansever, G. (2026) · International Congress on Human-Computer Interaction, Optimization and Robotic Applications (ICHORA) · doi:10.1109/ichora69329.2026.11537093
“Orman et al. [6] applied a hybrid CNN GRU model for cyberattack detection in industrial IoT networks and showed that temporal dependencies can improve anomaly identification.”
Smart Cyber Defense in Industry 4.0: AI-Powered Early Warning and Threat Prediction System
Agarwal, A., Gupta, P., & Rustagi, T. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-26352-0_8
Toward a Unified View of Cybersecurity Ontologies: A Systematic Review and Conceptual Consolidation
Gacitúa, R., & Diéguez, M. (2026) · Applied Sciences · doi:10.3390/app16126185
An Attention-Driven Explainable Deep Learning Framework for Multiclass IoT Cyberattack Detection
Monika., M., Ashokarao, G., Kumar, D., Brundha, K. M. P., Kate, C., & Kaliappan, S. (2026) · International Conference on Intelligent Systems and Computational Networks (ICISCN) · doi:10.1109/iciscn67954.2026.11566154
Machine Learning-Based Cyberattack Detection in IIoT Environments
Sivaramkrishnan, M., Sangeetha, A. R., Sabri, M. O., Geetha, R., Sravani, K. G., & Bhardwaj, N. (2026) · IEEE Nexo-Tech International Conference on Advanced Technologies and Innovations (ICATI) · doi:10.1109/icati69399.2026.11604284
RDO-DCNet: Red Deer Optimized Deep Learning Framework for Malware Detection in IIoT
Alwarsamy, V., Rethnaraj, J., Nagappan, M. M., & Patibandla, L. P. K. R. (2026) · International Journal of Computational Intelligence Systems · doi:10.1007/s44196-026-01392-y
“In 2025 Orman, A [34]. introduced a far more developed IDS framework based on DL models to improve cybersecurity in the IIoT setting; his analysis, which relied on DL models, is thus expected to make a major contribution, given the scarcity of such works in the literature.”
Song, B., & Yu, Z. (2026) · Research Square · doi:10.21203/rs.3.rs-10408343/v1
AI-Based Metrology-Centric Framework of Cyber-Physical Attacks in Software-Defined Electric Vehicles
Hammouda, K. B., Kanak, A., Sen, M. E., Cinar, B., Atalay, A. S., Ergün, S., Trabelsi, M., Trabelsi, R., & Abdelati, R. (2026) · IEEE International Workshop on Metrology for Automotive (MetroAutomotive) · doi:10.1109/metroautomotive69354.2026.11644669
“This compromises the integrity of sensor data and the trustworthiness of BMS decisions [3,4].”
Study of Emergence and Nonlinearity in IIoT Cybersecurity: A Pretest
Viswakumar, P., & Halawi, L. (2026) · IntechOpen eBooks · doi:10.5772/intechopen.1017531
Al-Shibly, I., Burgas, L., & Massana, J. (2026) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2026.1932015
“However, it also creates a broader and more accessible attack surface that can be exploited by cyber attackers (Orman, 2025).”
Sangeetha, B. M., Suguna, N., & Uma, S. M. (2026) · Journal of Critical Infrastructure Policy · doi:10.1002/jci3.70046
Metadata
- Authors
- Orman, A.
- Affiliations
- Ankara Yıldırım Beyazıt University (TR)
- Corresponding author
- Orman, Abdullah
- ORCID
- Orman, Abdullah
- Venue
- Applied Sciences
- Publisher
- MDPI AG
- Published
- 2025-03-13
- Volume
- 15
- Issue
- 6
- Pages
- 3121
- ISSN
- 2076-3417 (ISSN-L)
- OpenAlex
- W4408410698
- Cited by
- 41
- References
- 44
- Citations by year
- 2026: 29 · 2025: 12
- FWCI
- 17.33
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Applied Sciences (publishedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Topics
- Physical Sciences › Computer Science › Computer Networks and Communications › Network Security and Intrusion Detection
- Physical Sciences › Engineering › Control and Systems Engineering › Smart Grid Security and Resilience
- Physical Sciences › Computer Science › Hardware and Architecture › Network Packet Processing and Optimization
- Keywords
- cyberattack detection, Industrial Internet of Things, intrusion detection systems, SCADA systems, denial-of-service attacks, DDoS attacks, multilayer perceptron, convolutional neural networks, hybrid deep learning model, hyperparameter optimization, feature distribution
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.