Real-Time Intrusion Detection Based on Decision Fusion in Industrial Control Systems
The DOI matches its Crossref record; 34 of the 34 references it cites were found in a registry or an index.
Abstract
Industrial control systems (ICSs) are becoming increasingly interconnected as the rapid convergence of information technology (IT) and operation technology (OT) networks, and meanwhile massive attack surfaces have been exposed. However, traditional intrusion detection systems (IDSs) are difficult to be directly deployed in ICSs due to the hard real-time requirement and rare patching chance. Besides, the design of effective and practical IDSs is hampered by the lack of benchmarking ICS cybersecurity datasets. To bridge the gaps, this paper makes the first attempt by open-sourcing the developed ICS cybersecurity datasets and proposing a decision fusion based real-time IDS. Firstly, we design a customized cybersecurity dataset in a full-hardware and high-fidelity platform, including 7 types of cyber threats tailored for ICSs. The collected dataset includes network traffic, sensor readings, actuator status, and system parameters, providing the state-of-the-art benchmark dataset for ICSs consisting of cross-layer characteristics. Furthermore, we design an online decision fusion-based IDS by strategically integrating 4 widely-used machine learning models. The proposed IDS is deployed on a real-time running ethanol distillation, surpassing the performance of single detection models in terms of precision and F1-score, which substantially enhances intrusion detection accuracy and cybersecurity of ICS.
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
“Decision Tree, SVM, LSTM, and XGBoost detectors were trained separately on the hybrid dataset, and their decisions were then combined using hard and soft voting in a decisionlevel fusion scheme to compensate for individual model biases.”
From AI-Based Anomaly Detection in Industrial Control and Cyber–Physical Systems: A Data-Type-Oriented Systematic Review (2025) · cites this paper as [133]
In the citing paper
“The fused detector achieved higher detection accuracy and better generalization than any single model, demonstrating the feasibility of real-time hybrid-data anomaly detection that jointly considers cyber (communication anomalies) and physical (process anomalies) layers in ICS.”
From AI-Based Anomaly Detection in Industrial Control and Cyber–Physical Systems: A Data-Type-Oriented Systematic Review (2025) · cites this paper as [133]
In the citing paper
“Second, many frameworks perform decision-level fusion rather than strict feature-level fusion, aggregating per-model outputs via voting schemes or risk evaluation engines; this design simplifies deployment across diverse ICS domains because existing detectors can be reused while the fusion logic is tuned to plant-specific safety and criticality requirements [133-136].”
From AI-Based Anomaly Detection in Industrial Control and Cyber–Physical Systems: A Data-Type-Oriented Systematic Review (2025) · cites this paper as [133]
In the citing paper
“First, they explicitly combine detectors with heterogeneous inductive biases-tree ensembles, kernel methods, deep sequence models, and state observers-so that cyber-layer traffic anomalies and physical-layer process deviations are jointly reflected in the final decision, improving robustness under noisy hybrid data and nonstationary operating regimes [133-137].”
From AI-Based Anomaly Detection in Industrial Control and Cyber–Physical Systems: A Data-Type-Oriented Systematic Review (2025) · cites this paper as [133]
In the citing paper
“Xue et al. [133] proposed a decision-fusion-based real-time anomaly detection method designed to address the constraints of limited computational resources and strict realtime requirements in ICS.”
From AI-Based Anomaly Detection in Industrial Control and Cyber–Physical Systems: A Data-Type-Oriented Systematic Review (2025) · cites this paper as [133]
1 more claim about this paper
Create a free account to see every claim other papers make about this one.
Citations
Cites
XGBoost: A Scalable Tree Boosting System
Chen, T., & Guestrin, C. (2016) · Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2939672.2939785 · Cited by 54,569
Scikit-learn: Machine Learning in Python
(2011) · Journal of Machine Learning Research · doi:10.5555/1953048.2078195 · Cited by 8,539
Greff, K., Srivastava, R. K., Koutnik, J., Steunebrink, B. R., & Schmidhuber, J. (2017) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2016.2582924 · Cited by 6,955
Moustafa, N., & Slay, J. (2015) · 2015 Military Communications and Information Systems Conference (MilCIS) · doi:10.1109/milcis.2015.7348942 · Cited by 4,033
Survey of intrusion detection systems: Techniques, datasets and challenges
Khraisat, A., Gondal, I., Vamplew, P., & Kamruzzaman, J. (2019) · Cybersecurity · doi:10.1186/s42400-019-0038-7 · Cited by 2,024
Stuxnet: Dissecting a cyberwarfare weapon
Langner, R. (2011) · IEEE Security & Privacy Magazine · doi:10.1109/msp.2011.67 · Cited by 1,922
Ahmad, Z., Shahid Khan, A., Wai Shiang, C., Abdullah, J., & Ahmad, F. (2021) · Transactions on Emerging Telecommunications Technologies · doi:10.1002/ett.4150 · Cited by 1,288
A survey of intrusion detection techniques in Cloud
Modi, C., Patel, D., Borisaniya, B., Patel, H., Patel, A., & Rajarajan, M. (2013) · Journal of Network and Computer Applications · doi:10.1016/j.jnca.2012.05.003 · Cited by 889
SWaT: a water treatment testbed for research and training on ICS security
Mathur, A. P., & Tippenhauer, N. O. (2016) · 2016 International Workshop on Cyber-physical Systems for Smart Water Networks (CySWater) · doi:10.1109/cyswater.2016.7469060 · Cited by 878
A survey of intrusion detection techniques for cyber-physical systems
Mitchell, R., & Chen, I.-R. (2014) · ACM Computing Surveys · doi:10.1145/2542049 · Cited by 768
Research works printed but not linked: 1
- Case, 2016, Analysis of the cyber attack on the ukrainian power grid, Electricity Inf. Sharing Anal. Center, 388, 3
Cited by
Advanced Machine Learning in Smart Grids: An overview
Noura, H., Yaacoub, J.-P. A., Salman, O., & Chehab, A. (2025) · Internet of Things and Cyber-Physical Systems · doi:10.1016/j.iotcps.2025.05.002 · Cited by 32
Lu, K., Yang, Y.-W., Zeng, G., Peng, C., Geng, G., & Weng, J. (2025) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2025.3572510 · Cited by 28
Seo, J. K., Lee, J., Kim, B., Shim, W., & Seo, J. T. (2025) · Electronics · doi:10.3390/electronics15010020 · Cited by 15
Cyber-Physical Real-Time Digital Simulation for Cybersecurity Analysis in Microgrids
Qiu, D., Liu, M., Zhang, R., Luo, T., Griffo, A., & Zhang, X. (2025) · IEEE Transactions on Industrial Cyber-Physical Systems · doi:10.1109/ticps.2025.3569640 · Cited by 22
Self-citationFunctional Safety Analysis and Mitigation in Power Systems: A Cyber‐Physical Perspective
Jia, S., & Guo, Q. (2025) · Energy internet. · doi:10.1049/ein2.70007 · Cited by 11
“Notable examples include the CPS security testing platform co‐developed by Zhejiang University and SGCC [112], which facilitates hands‐on system attack and defence research in a controlled environment.”
Explainable AI-Driven Threat Detection and Response for Industrial IoT
Khandan, S., Beyazgul, D., Jogunola, O., Tsado, Y., & Dargahi, T. (2025) · IEEE Conference on Communications and Network Security · doi:10.1109/cns66487.2025.11195011 · Cited by 6
“Researchers suggest that models trained on a combined dataset provide better generalisation to enhance detection accuracy and resilience [6].”
Intrusion Detection Datasets for IIoT and ICS: A Taxonomic Review with a Decision-Aid Scoring Rubric
Termanini, A., Bourdoucen, H., Al‐Abri, D., & Maashri, A. A. (2026) · Sensors · doi:10.3390/s26134099 · Cited by 9
“For S7Comm, the strongest accessible choices are Rodofile [34], ICS-NAD [46], and EDS [49], with TLIGHT [43] as a specification-level reference for Siemens S7 PLC scenarios.”
A probabilistic cost-benefit analysis approach for cyberattack path evaluation
Zhang, J., Zio, E., Ma, C., Liu, K., & Wang, W. (2025) · Reliability Engineering & System Safety · doi:10.1016/j.ress.2025.111255 · Cited by 8
MIDES: A multi-layer Intrusion Detection System using ensemble machine learning
Agate, V., Paola, A. D., Ferraro, P., & Re, G. L. (2025) · International Journal of Intelligent Networks · doi:10.1016/j.ijin.2025.09.001 · Cited by 11
Kumar, G. H., Shelke, N. M., Pimpalkar, A. P., Saini, D. K. J. B., Prajwalasimha, S. N., & Kumar, Y. D. (2025) · International Conference on Networks, Multimedia and Information Technology (NMITCON) · doi:10.1109/nmitcon65824.2025.11188236 · Cited by 5
“The section explains the simulation environment together with datasets and evaluation metrics which validate the proposed Zero Trust-enabled Digital Twin (ZT-DT) framework before presenting a performance comparison with baseline and state-of-the-art (SOTA) approaches[16][17][18].”
Distributed Set-Membership Estimation Over Delayed and Attacked Sensor Networks
Bao, S., Li, J., Liu, C., Xu, Y., Huang, T., & Rutkowski, L. (2025) · IEEE Transactions on Industrial Cyber-Physical Systems · doi:10.1109/ticps.2025.3632249 · Cited by 3
Decentralized CNN Integrated Federated Learning for Intrusion Detection System
Dandapat, A., & Mondal, B. (2025) · OPJU International Technology Conference on Smart Computing for Innovation and Advancement in Industry (OTCON) · doi:10.1109/otcon65728.2025.11071097 · Cited by 4
“On any questionable activity, the system sends out notifications or takes aggressive action against it [1] [9].”
Niu, Y., Han, X., He, C., Wang, Y., Cao, Z., & Zhou, D. (2025) · Applied Sciences · doi:10.3390/app15148032 · Cited by 7
Comparative Analysis of Traditional and Ensemble Learning Models for Network Security System
Verma, A., & Rathod, M. (2025) · International Conference on Computational, Communication and Information Technology (ICCCIT) · doi:10.1109/icccit62592.2025.10928149 · Cited by 2
“In a nutshell, it combines several ML models and implements an automated approach to improve the accuracy of ID as well as the security posture in real time deployments [4].”
Next-Generation Intrusion Detection: Navigating Challenges and Embracing AI
Shivhare, M., Dhir, S., & Shrivastava, S. K. (2025) · International Conference on Pervasive Computational Technologies (ICPCT) · doi:10.1109/icpct64145.2025.10940300 · Cited by 2
“Isolation Forests have good capabilities to detect intrusions[17][14].”
Real–Time File Integrity Detection System
Rajkumar, E., Santhosh, S. J., Saranraj, M., & Hariharan, D. (2025) · IEEE International Conference on Blockchain and Distributed Systems Security (ICBDS) · doi:10.1109/icbds67396.2025.11376605 · Cited by 1
“This holistic integration ensures comprehensive protection, operational efficiency, and compliance with modern cybersecurity standards such as ISO 27001 and NIST [14].”
A lightweight intrusion detection method for industrial network control systems
Lei, M., Zhao, H., He, Y., Zhao, J., Zhang, Y., & Li, X. (2025) · International Conference on Advanced Control Systems and Automation Technologies (ACSAT) · doi:10.1109/acsat68407.2025.11407363 · Cited by 1
“Xue et al.[9] proposed decision fusion for real-time detection, and Mohy-Eddine et al.[10] employed ensemble learning for IIoT security.”
TL-SOC: A Hybrid Decision-Centric Intrusion Detection Framework for Security Operations Centers
Lotfi, I., & Mandar, M. (2026) · Advances in Science Technology and Engineering Systems Journal · doi:10.25046/aj110204 · Cited by 1
Saidane, S., Telch, F., Shahin, K., Gkonis, P. K., & Granelli, F. (2026) · Array · doi:10.1016/j.array.2026.100896 · Cited by 1
Kumar, A., Naik, K. R., Samal, S. K., & Nirala, A. K. (2026) · Applied Soft Computing · doi:10.1016/j.asoc.2026.116018 · Cited by 2
Attack Detection Using Decision Tree and Naïve Bayes with Bat Algorithm-Based Feature Selection
Abualhaj, M. M., Daoud, M. S., Al-Allawee, A., Almimi, H., Anbar, M., & Munther, A. (2025) · International Conference on Intelligent Data Science Technologies and Applications (IDSTA) · doi:10.1109/idsta66210.2025.11202806 · Cited by 1
“IDS are willing to find most of the attacks that are evade the firewall [3,4,5].”
Intelligent Defense For Smart Grids: Leveraging Resgen And Cho Models For Iot Security
Aslam, N. M., & Shilaja, C. (2025) · International Conference on Disruptive Technologies (ICDT) · doi:10.1109/icdt63985.2025.10986411
“In this respect, Smart Grid security would concern the protection of every single device, the resilience of the general network from sophisticated cyber-attacks [4].”
Optimized Feature Selection for Enhanced Network Attack Detection Using Bat Algorithm
Abualhaj, M. M., Al-Allawee, A., Almomani, O., & Anbar, M. (2025) · doi:10.1109/iceeng64546.2025.11031370 · Cited by 2
“Despite the elevated incidence of false alarms in anomaly detection, it effectively identifies new attacks, and numerous studies have advocated for its implementation [4,5].”
Zhou, M., & Che, X. (2025) · ICT Express · doi:10.1016/j.icte.2025.07.003
Chen, Y. H., Chen, S.-Y., & Lai, C. (2025) · Automation · doi:10.3390/automation6040055
“Completing smart manufacturing based on a series of technologies is an essential goal for the industry to move towards Industry 4.0 [4].”
InfluentialJiang, X., Zhang, W., Zhang, X., & Wang, Y. (2025) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2025.3640272
“Their primary objective is to guarantee the e ffi cient and secure operation of the network and o ff er swift and precise control across various industries [5].”
Xiong, W., Li, S., Li, S., & Chen, X. (2025) · Transactions of the Institute of Measurement and Control · doi:10.1177/01423312251396220
Resource Orchestration Method for Industrial Control Software Security Crowdsourcing Platform
Tong, F., Dong, J., Zhao, D., Xu, L., & Yu, F. (2025) · International Conference on High Performance Compilation, Computing and Communications (HP3C) · doi:10.1145/3774949.3774955
Ke, Y., Zhan, X., Wu, J., & Cheng, L. (2026) · International Journal of Robust and Nonlinear Control · doi:10.1002/rnc.70451
SoK: Hospital Medical Devices as Industrial Control Systems (ICS) - Exposure and Vulnerability
Bailey, J. M., Yurcik, W. J., Saydjari, O. S., Avelino, R. D. S., Vieira, J. L., Umbelino, P., & Pluta, G. (2025) · Annual Computer Security Applications Conference Workshops (ACSAC Workshops) · doi:10.1109/acsacw69556.2025.00018
A collaborative intelligence framework for distributed security defense in Industry 4.0
Yang, L., Wang, J., Di, J., & Zhou, Z. (2026) · Journal of the Franklin Institute · doi:10.1016/j.jfranklin.2026.108563 · Cited by 1
Nassar, A. A., & Morsi, W. G. (2026) · Sustainable Energy Grids and Networks · doi:10.1016/j.segan.2026.102266
A Stability-Centric Framework for Lightweight and Explainable Intrusion Detection
Alhalangy, A., Alkhamis, S. A., & Abouelkheir, E. (2026) · Future Internet · doi:10.3390/fi18060305
Jamal, M. B., Javeed, D., Adil, M., & Zhao, Y. (2026) · IEEE Internet of Things Journal · doi:10.1109/jiot.2026.3701887
“Some among others, includes control systems [15], power systems [16], and maritime systems [17].”
Generating Black-Box Adversarial Examples for Industrial Control Systems via Immune Co-Evolution
Huang, C., He, J., Li, W., Li, T., Ma, W., Fang, W., & Lan, X. (2026) · IEEE Internet of Things Journal · doi:10.1109/jiot.2026.3705384
“Every feature corresponds to a physical measurement whose modification must satisfy both protocol constraints and physical laws [27].”
InfluentialChang, J. A., & Vighio, M. S. (2025) · International Journal of Innovations in Science and Technology · doi:10.33411/ijist/1698
GenTI: Benchmarking LLMs for Autonomous IDPS Rule Generation for Unseen Attacks
Hadi, H. J., Khan, M. K., Ahmad, N., Yasmin, R., & Shoker, A. (2026) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2026.3716998 · Cited by 5
“These advances include feature-based learning [35], [36] [35], [37], representation learning [38], [39] [40], [41] [42], sequential models [43], [44], hybrid pipelines [45], [46] [47], [46], Fusion based [48], [49] [50] and Multi-Tier [51], [52] [53].”
Tang, Y., Ni, L., Zhang, J., & Liang, Y. (2026) · Information Processing & Management · doi:10.1016/j.ipm.2026.105099
Li, Q. (2026) · Procedia Computer Science · doi:10.1016/j.procs.2026.07.291
Exploring Industry 5.0: Architecture, Threat Landscape, and Security Strategies
Hamouda, D., Ferrag, M. A., & Kouahla, Z. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-26031-4_7
Attention‐Driven Real‐Time Fusion for Robust Intrusion Detection in Control Networks
Rehman, A. U., Khan, S., Khan, M. A., Altameem, A., Bharany, S., Taye, B. M., & Almogren, A. (2026) · IET Information Security · doi:10.1049/ise2/2349648
Xue, Y., Yang, Z., Yau, D. K. Y., & Deng, R. (2026) · IEEE Transactions on Industrial Cyber-Physical Systems · doi:10.1109/ticps.2026.3735617
Self-citationAich, P. R., Sowmyha, S., Dinesh, M., Kanagaraj, G., Senthilkumar, A., & Karimunnisa, S. (2026) · SN Computer Science · doi:10.1007/s42979-026-05404-8
Metadata
- Authors
- Xue, Y., Pan, J., Geng, Y., Yang, Z., Liu, M., & Deng, R.
- Affiliations
- State Key Laboratory of Industrial Control Technology (CN)
- PLA Information Engineering University (CN)
- Singapore University of Technology and Design (SG)
- University of Sheffield (GB)
- Venue
- IEEE Transactions on Industrial Cyber-Physical Systems
- Published
- 2024
- Volume
- 2
- Pages
- 143-153
- ISSN
- 2832-7004 (ISSN-L)
- OpenAlex
- W4399110828
- Cited by
- 43
- References
- 34
- Citations by year
- 2026: 17 · 2025: 26
- FWCI
- 7.18
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Locations
- IEEE Transactions on Industrial Cyber-Physical Systems (publishedVersion)
- Funders
- National Natural Science Foundation of China (62293503, 62293502, 62293500, 62073285, 62303411)
- Natural Science Foundation of Zhejiang Province (LR23F030001)
- Xiaomi Foundation
- Fundamental Research Funds for the Central Universities
- Key Lab of CS&AUS of Zhejiang Province
- 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 › Artificial Intelligence › Artificial Immune Systems Applications
- Keywords
- intrusion detection, industrial control systems, decision fusion, real-time detection, ICS cybersecurity, benchmark dataset, ethanol distillation, network traffic, sensor readings, machine learning model integration, IT-OT convergence
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.