Deep Learning-Based Cyber–Physical Feature Fusion for Anomaly Detection in Industrial Control Systems
Open accessThe DOI matches its Crossref record; 35 of the 35 references it cites were found in a registry or an index.
Abstract
In this paper, we propose an unsupervised anomaly detection method based on the Autoencoder with Long Short-Term Memory (LSTM-Autoencoder) network and Generative Adversarial Network (GAN) to detect anomalies in industrial control system (ICS) using cyber–physical fusion features. This method improves the recall of anomaly detection and overcomes the challenges of unbalanced datasets and insufficient labeled samples in ICS. As a first step, additional network features are extracted and fused with physical features to create a cyber–physical dataset. Following this, the model is trained using normal data to ensure that it can properly reconstruct the normal data. In the testing phase, samples with unknown labels are used as inputs to the model. The model will output an anomaly score for each sample, and whether a sample is anomalous depends on whether the anomaly score exceeds the threshold. Whether using supervised or unsupervised algorithms, experimentation has shown that (1) cyber–physical fusion features can significantly improve the performance of anomaly detection algorithms; (2) the proposed method outperforms several other unsupervised anomaly detection methods in terms of accuracy, recall, and F1 score; (3) the proposed method can detect the majority of anomalous events with a low false negative rate.
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
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
“The model judges anomalies based on reconstruction capability under normal conditions and demonstrates approximately a 6% improvement in detection accuracy compared to single-modality approaches.”
From AI-Based Anomaly Detection in Industrial Control and Cyber–Physical Systems: A Data-Type-Oriented Systematic Review (2025) · cites this paper as [122]
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
“First, many approaches explicitly synchronize cyber-layer events with physical-layer behavior on a common time axis to detect cyber-physical inconsistencies that single-domain detectors would miss [122-129].”
From AI-Based Anomaly Detection in Industrial Control and Cyber–Physical Systems: A Data-Type-Oriented Systematic Review (2025) · cites this paper as [122]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“The authors extract network features such as protocol fields and payload size from Modbus TCP packets and combine them with process sensor data to construct cyberphysical fusion features.”
From AI-Based Anomaly Detection in Industrial Control and Cyber–Physical Systems: A Data-Type-Oriented Systematic Review (2025) · cites this paper as [122]
The cited source says what the claim attributes to it.
In the citing paper
“Du et al. [122] proposed an unsupervised hybrid data fusion-based anomaly detection method that combines an LSTM-Autoencoder with a GAN, using a self-constructed ICS dataset that fuses network traffic from the cyber layer and sensor readings from the physical layer.”
From AI-Based Anomaly Detection in Industrial Control and Cyber–Physical Systems: A Data-Type-Oriented Systematic Review (2025) · cites this paper as [122]
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
Liu, F. T., Ting, K. M., & Zhou, Z.-H. (2008) · 2008 Eighth IEEE International Conference on Data Mining · doi:10.1109/icdm.2008.17 · Cited by 6,601
MAD-GAN: Multivariate Anomaly Detection for Time Series Data with Generative Adversarial Networks
Li, D., Chen, D., Jin, B., Shi, L., Goh, J., & Ng, S.-K. (2019) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-30490-4_56 · Cited by 1,185
Machine Learning and Deep Learning Methods for Intrusion Detection Systems: A Survey
Liu, H., & Lang, B. (2019) · Applied Sciences · doi:10.3390/app9204396 · Cited by 1,133
USAD: UnSupervised Anomaly Detection on Multivariate Time Series
Audibert, J., Michiardi, P., Guyard, F., Marti, S., & Zuluaga, M. A. (2020) · Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining · doi:10.1145/3394486.3403392 · Cited by 1,094
TranAD: deep transformer networks for anomaly detection in multivariate time series data
Tuli, S., Casale, G., & Jennings, N. R. (2022) · Proceedings of the VLDB Endowment · doi:10.14778/3514061.3514067 · Cited by 1,063
Enhancing one-class support vector machines for unsupervised anomaly detection
Amer, M., Goldstein, M., & Abdennadher, S. (2013) · Proceedings of the ACM SIGKDD Workshop on Outlier Detection and Description · doi:10.1145/2500853.2500857 · Cited by 427
Generative Adversarial Networks: A Survey Toward Private and Secure Applications
Cai, Z., Xiong, Z., Xu, H., Wang, P., Li, W., & Pan, Y. (2022) · ACM Computing Surveys · doi:10.1145/3459992 · Cited by 376
Detecting Cyber Attacks in Industrial Control Systems Using Convolutional Neural Networks
Kravchik, M., & Shabtai, A. (2018) · Proceedings of the 2018 Workshop on Cyber-Physical Systems Security and PrivaCy · doi:10.1145/3264888.3264896 · Cited by 355
Machine learning for power system disturbance and cyber-attack discrimination
Borges Hink, R. C., Beaver, J. M., Buckner, M. A., Morris, T., Adhikari, U., & Pan, S. (2014) · 2014 7th International Symposium on Resilient Control Systems (ISRCS) · doi:10.1109/isrcs.2014.6900095 · Cited by 313
A Unified Deep Learning Anomaly Detection and Classification Approach for Smart Grid Environments
Siniosoglou, I., Radoglou-Grammatikis, P., Efstathopoulos, G., Fouliras, P., & Sarigiannidis, P. (2021) · IEEE Transactions on Network and Service Management · doi:10.1109/tnsm.2021.3078381 · Cited by 266
Industrial Control Systems: Cyberattack trends and countermeasures
Alladi, T., Chamola, V., & Zeadally, S. (2020) · Computer Communications · doi:10.1016/j.comcom.2020.03.007 · Cited by 265
Fahim, M., & Sillitti, A. (2019) · IEEE Access · doi:10.1109/access.2019.2921912 · Cited by 238
Multi-level Anomaly Detection in Industrial Control Systems via Package Signatures and LSTM Networks
Feng, C., Li, T., & Chana, D. (2017) · 2017 47th Annual IEEE/IFIP International Conference on Dependable Systems and Networks (DSN) · doi:10.1109/dsn.2017.34 · Cited by 231
TABOR: A Graphical Model-based Approach for Anomaly Detection in Industrial Control Systems
Lin, Q., Adepu, S., Verwer, S., & Mathur, A. P. (2018) · ACM Asia Conference on Computer and Communications Security (ASIA CCS) · doi:10.1145/3196494.3196546 · Cited by 211
An Evaluation of Machine Learning Methods to Detect Malicious SCADA Communications
Beaver, J. M., Borges-Hink, R. C., & Buckner, M. A. (2013) · 2013 12th International Conference on Machine Learning and Applications · doi:10.1109/icmla.2013.105 · Cited by 189
Rectified Linear Postsynaptic Potential Function for Backpropagation in Deep Spiking Neural Networks
Zhang, M., Wang, J., Wu, J., Belatreche, A., Amornpaisannon, B., Zhang, Z., Miriyala, V. P. K., Qu, H., Chua, Y., Carlson, T. E., et al. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2021.3110991 · Cited by 174
Unsupervised Anomaly Detection in Time Series Using LSTM-Based Autoencoders
Provotar, O. I., Linder, Y. M., & Veres, M. M. (2019) · 2019 IEEE International Conference on Advanced Trends in Information Theory (ATIT) · doi:10.1109/atit49449.2019.9030505 · Cited by 169
Khan, R., Maynard, P., McLaughlin, K., Laverty, D., & Sezer, S. (2016) · Electronic Workshops in Computing · doi:10.14236/ewic/ics2016.7 · Cited by 165
Ahmed, C. M., Zhou, J., & Mathur, A. P. (2018) · Annual Computer Security Applications Conference · doi:10.1145/3274694.3274748 · Cited by 126
Multilevel Attention-Based Sample Correlations for Knowledge Distillation
Gou, J., Sun, L., Yu, B., Wan, S., Ou, W., & Zhang, Y. (2022) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2022.3209672 · Cited by 126
GAN-Based Data Augmentation Strategy for Sensor Anomaly Detection in Industrial Robots
Lu, H., Du, M., Qian, K., He, X., & Wang, K. (2021) · IEEE Sensors Journal · doi:10.1109/jsen.2021.3069452 · Cited by 114
Benaddi, H., Jouhari, M., Ibrahimi, K., Ben‐Othman, J., & Amhoud, E. M. (2022) · Sensors · doi:10.3390/s22218085 · Cited by 110
A Hardware-in-the-Loop Water Distribution Testbed Dataset for Cyber-Physical Security Testing
Faramondi, L., Flammini, F., Guarino, S., & Setola, R. (2021) · IEEE Access · doi:10.1109/access.2021.3109465 · Cited by 101
Cyber-attack detection in SCADA systems using temporal pattern recognition techniques
Kalech, M. (2019) · Computers & Security · doi:10.1016/j.cose.2019.03.007 · Cited by 90
Zhang, M., Qu, H., Belatreche, A., Chen, Y., & Zhang, Y. (2018) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2018.2833077 · Cited by 84
AE-CGAN Model based High Performance Network Intrusion Detection System
Lee, J., & Park, K. (2019) · Applied Sciences · doi:10.3390/app9204221 · Cited by 76
Ayodeji, A., Liu, Y.-K., Chao, N., & Yang, L.-Q. (2020) · Nuclear Engineering and Technology · doi:10.1016/j.net.2020.05.012 · Cited by 66
Advanced correlation-based anomaly detection method for predictive maintenance
Zhao, P., Kurihara, M., Tanaka, J., et al. (2017) · IEEE Conference on Prognostics and Health Management · doi:10.1109/icphm.2017.7998309 · Cited by 65
Anomaly Detection for Industrial Control Systems Using K-Means and Convolutional Autoencoder
Chang, C.-P., Hsu, W.-C., & Liao, I. (2019) · International Conference on Software, Telecommunications and Computer Networks (SoftCOM) · doi:10.23919/softcom.2019.8903886 · Cited by 49
Abnormal detection method of industrial control system based on behavior model
Zhanwei, S., & Zenghui, L. (2019) · Computers & Security · doi:10.1016/j.cose.2019.03.009 · Cited by 44
ShadowPLCs: A Novel Scheme for Remote Detection of Industrial Process Control Attacks
Liu, J., Lin, X. S., Chen, X., et al. (2020) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2020.3046267 · Cited by 31
Abnormal Data Classification Using Time-Frequency Temporal Logic
Nguyen, L. V., Kapinski, J. P., Jin, X., et al. (2017) · International Conference on Hybrid Systems: computation and control · doi:10.1145/3049797.3049809 · Cited by 19
Assessment of Cyber-Physical Intrusion Detection and Classification for Industrial Control Systems
Müller, N., Ziras, C., & Heussen, K. (2022) · IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm) · doi:10.1109/smartgridcomm52983.2022.9961010 · Cited by 18
A fast intra coding algorithm for HEVC by jointly utilizing naive Bayesian and SVM
Huang, Y., Wang, D., Sun, Y., et al. (2020) · Multimedia Tools and Applications · doi:10.1007/s11042-020-08882-x · Cited by 12
Self-citationA Hybrid Association Rule-Based Method to Detect and Classify Botnets
Huang, Y., Lu, J., Tang, H., & Liu, X. (2021) · Security and Communication Networks · doi:10.1155/2021/1028878 · Cited by 7
Self-citation
Research works printed but not linked: 2
- Bank, D., Koenigstein, N., and Giryes, R. (2020). Autoencoders. arXiv.
- Zhang, 2019, Abnormal flow monitoring of industrial control network based on convolutional neural network, J. Comput. Appl., 39, 1512
Cited by
Unsupervised Learning Approach for Anomaly Detection in Industrial Control Systems
Choi, W.-H., & Kim, J. (2024) · Applied System Innovation · doi:10.3390/asi7020018 · Cited by 74
Seo, J. K., Lee, J., Kim, B., Shim, W., & Seo, J. T. (2025) · Electronics · doi:10.3390/electronics15010020 · Cited by 15
Metadata
- Authors
- Du, Y., Huang, Y., Wan, G., & He, P.
- Affiliations
- Chengdu University of Information Technology (CN)
- University of Pittsburgh (US)
- Corresponding author
- Huang, Yuanyuan
- Venue
- Mathematics
- Publisher
- MDPI AG
- Published
- 2022-11-20
- Volume
- 10
- Issue
- 22
- Pages
- 4373
- ISSN
- 2227-7390 (ISSN-L)
- OpenAlex
- W4309737874
- Cited by
- 24
- References
- 35
- Citations by year
- 2026: 5 · 2025: 9 · 2024: 7 · 2023: 3
- FWCI
- 1.56
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Mathematics (publishedVersion, cc-by)
- RePEc: Research Papers in Economics (submittedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- Natural Science Foundation of Sichuan Province (2022NSFSC0557, 62102049, 62076042, 2021YFSY0012, 2021YFG0332)
- National Natural Science Foundation of China (2022NSFSC0557, 62102049, 62076042, 2021YFSY0012, 2021YFG0332)
- Key Research and Development Project of Sichuan (2022NSFSC0557, 62102049, 62076042, 2021YFSY0012, 2021YFG0332)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Anomaly Detection Techniques and Applications
- Physical Sciences › Engineering › Control and Systems Engineering › Fault Detection and Control Systems
- Physical Sciences › Computer Science › Computer Networks and Communications › Network Security and Intrusion Detection
- Keywords
- industrial control systems, anomaly detection, LSTM autoencoder, generative adversarial networks, unsupervised anomaly detection, class imbalance, industrial cybersecurity
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.