TSMixAD: A Time-Series Anomaly Detection Framework for Industrial Control Systems Incorporating Time-Frequency Domain Data Augmentation Techniques
Open accessAbstract
Industrial control systems are an important part of the nation's critical infrastructure, and effective anomaly detection is important to ensure system safety. However, the challenges of anomaly sample scarcity and unequal data distribution in industrial control systems limit the effectiveness of existing anomaly detection methods. Therefore, this paper proposes a time-series anomaly detection framework, TSMixAD, which integrates time-frequency domain enhancement. The Mixup method based on Dirichlet distribution is adopted in the time domain, and frequency mask, noise injection and frequency shift enhancement are adopted in the frequency domain to improve the classification ability of a sample. Tcn-transformer hybrid encoder is constructed, in which TCN is responsible for extracting local time dependencies efficiently, and Transformer is responsible for global association modeling, so as to improve the robustness of anomaly detection. We validate our approach on two publicly available industrial control system datasets, SWaT and WADI.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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?
Process data are particularly suitable for attacks that perturb the physical process state while keeping network-level statistics relatively unchanged, such as false data injection, malicious command or parameter manipulation, process-oriented attacks, and stealthy drifts in sensor trajectories.
“First, process data are particularly suitable for attacks that perturb the physical process state while keeping network-level statistics relatively unchanged-such as false data injection, malicious command or parameter manipulation, process-oriented attacks, and stealthy drifts in sensor trajectories [67,69-73,75,76].”
From AI-Based Anomaly Detection in Industrial Control and Cyber–Physical Systems: A Data-Type-Oriented Systematic Review (2025) · cites this paper as [76]
Split into 2 atoms — 0 confirmed, 1 partially supported, 0 disputed, 0 misattributed, 1 unverifiable. Expand the claim to see per-atom verdicts.
Experimental — accuracy not yet measuredThe distribution of datasets shows a strong reliance on SWaT and WADI for benchmarking prediction-residual-based methods, with additional evidence from custom-built avionics, robotics, temperature-control, offshore wind farm, and simulation-based CPS testbeds.
“Finally, the distribution of datasets shows a strong reliance on SWaT and WADI for benchmarking prediction-residual-based methods, with additional evidence from custombuilt avionics, robotics, temperature-control, offshore wind farm, and simulation-based CPS testbeds [67-73,75,76].”
From AI-Based Anomaly Detection in Industrial Control and Cyber–Physical Systems: A Data-Type-Oriented Systematic Review (2025) · cites this paper as [76]
Split into 2 atoms — 0 confirmed, 2 partially supported, 0 disputed, 0 misattributed, 0 unverifiable. Expand the claim to see per-atom verdicts.
Experimental — accuracy not yet measuredSong et al. [76] proposed TSMixAD, a framework that integrates time-frequency domain data augmentation for sensor time-series collected from SWaT and WADI processes.
“From the perspective of time-series anomaly detection using process data, Song et al. [76] proposed TSMixAD, a framework that integrates time-frequency domain data augmentation for sensor time-series collected from SWaT and WADI processes.”
From AI-Based Anomaly Detection in Industrial Control and Cyber–Physical Systems: A Data-Type-Oriented Systematic Review (2025) · cites this paper as [76]
Prediction-residual-oriented methods are powerful for detecting subtle and coordinated process anomalies, including multi-point stealthy attacks that forge SCADA histories or slowly drive the system toward unsafe states.
“Third, in terms of detection capability and failure modes, the results indicate that prediction-residual-oriented methods are powerful for detecting subtle and coordinated process anomalies, including multi-point stealthy attacks that forge SCADA histories or slowly drive the system toward unsafe states [69,72,73,75,76].”
From AI-Based Anomaly Detection in Industrial Control and Cyber–Physical Systems: A Data-Type-Oriented Systematic Review (2025) · cites this paper as [76]
Section 4.3 reports that TSMixAD detects anomalies on SWaT and WADI, while Section 3.3 describes training with cross-entropy loss. Neither passage addresses the claimed capability of prediction-residual-oriented methods to detect coordinated or stealthy attacks. Searches for prediction residuals, forged SCADA histories, and gradual unsafe-state attacks found no supporting passage in our copy. (LLM, conf=0.77)
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.
Cites
CutPaste: Self-Supervised Learning for Anomaly Detection and Localization
Li, C.-L., Sohn, K., Yoon, J., & Pfister, T. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00954 · Cited by 1,107 · see citing works
Deep Learning for Time Series Anomaly Detection: A Survey
Darban, Z. Z., Webb, G. I., Pan, S., Aggarwal, C. C., & Salehi, M. (2024) · ACM Computing Surveys · doi:10.1145/3691338 · Cited by 743 · see citing works
DCdetector: Dual Attention Contrastive Representation Learning for Time Series Anomaly Detection
Yang, Y., Zhang, C., Zhou, T., Wen, Q., & Sun, L. (2023) · Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining · doi:10.1145/3580305.3599295 · Cited by 387 · see citing works
Time Series Anomaly Detection Using Convolutional Neural Networks and Transfer LearningPreprint
Wen, T., & Keyes, R. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.13628 · Cited by 132 · see citing works
Cybersecurity for Industrial IoT (IIoT): Threats, countermeasures, challenges and future directions
Mekala, S. H., Baig, Z., Anwar, A., & Zeadally, S. (2023) · Computer Communications · doi:10.1016/j.comcom.2023.06.020 · Cited by 111 · see citing works
RobustTAD: Robust Time Series Anomaly Detection via Decomposition and Convolutional Neural NetworksPreprint
Gao, J., Song, X., Wen, Q., Wang, P., Sun, L., & Xu, H. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2002.09545 · Cited by 102 · see citing works
Kong, L., Yu, J., Tang, D., Song, Y., & Han, D. (2023) · IEEE Sensors Journal · doi:10.1109/jsen.2023.3260563 · Cited by 30 · see citing works
Self-citationJeong, Y., Yang, E., Ryu, J. H., et al. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2305.04468 · Cited by 15 · see citing works
Flagged first, then by citations
Research works printed but not linked: 18
- Pang G, Shen C, Cao L, et al. Deep learning for anomaly detection: A review[J]. ACM computing surveys (CSUR), 2021, 54(2): 1-38.
- Kumar P, Bhatnagar R, Gaur K, et al. Classification of imbalanced data: review of methods and applications[C]//IOP conference series: materials science and engineering. IOP Publishing, 2021, 1099(1): 012077.
- Le Guennec A, Malinowski S, Tavenard R. Data augmentation for time series classification using convolutional neural networks[C]//ECML/PKDD workshop on advanced analytics and learning on temporal data. 2016.
- Guo P, Yang H, Sano A. Empirical study of mix-based data augmentation methods in physiological time series data[C]//2023 IEEE 11th International Conference on Healthcare Informatics (ICHI). IEEE, 2023: 206-213.
- Yoon J, Jarrett D, Van der Schaar M. Time-series generative adversarial net- works[J]. Advances in neural information processing systems, 2019, 32.
- Raileanu R, Goldstein M, Yarats D, et al. Automatic data augmentation for general- ization in reinforcement learning[J]. Advances in Neural Information Processing Systems, 2021, 34: 5402-5415.
- Li D, Chen D, Jin B, et al. MAD-GAN: Multivariate anomaly detection for time series data with generative adversarial networks[C]//International conference on artificial neural networks. Cham: Springer International Publishing, 2019: 703-716.
- Toor A A, Lin J C, Gran E G, et al. An Explainable Deep Learning-based Approach for Multivariate Time Series Anomaly Detection in IoT[C]//2023 International Conference on Frontiers of Information Technology (FIT). IEEE, 2023: 108-113.
- Li L, Yan J, Wen Q, et al. Learning robust deep state space for unsupervised anom- aly detection in contaminated time-series[J]. IEEE Transactions on Knowledge and Data Engineering, 2022, 35(6): 6058-6072.
- Mir A A, Zuhairi M F, Musa S, et al. Adaptive anomaly detection in dynamic graph networks[C]//2024 International Visualization, Informatics and Technol- ogy Conference (IVIT). IEEE, 2024: 200-206.
- Zhang K, Jiang Y, Seversky L, et al. Federated variational learning for anomaly detection in multivariate time series[C]//2021 IEEE International Performance, Computing, and Communications Conference (IPCCC). IEEE, 2021: 1-9.
- Zong B, Song Q, Min M R, et al. Deep autoencoding gaussian mixture model for unsupervised anomaly detection[C]//International conference on learning representations. 2018.
- Xu J, Wu H, Wang J, et al. Anomaly transformer: Time series anomaly detection with association discrepancy[J]. arXiv preprint arXiv:2110.02642, 2021. · arXiv
- Mathur A P, Tippenhauer N O. SWaT: A water treatment testbed for research and training on ICS security[C]//2016 international workshop on cyber-physical systems for smart water networks (CySWater). IEEE, 2016: 31-36.
- Kim S, Choi K, Choi H S, et al. Towards a rigorous evaluation of time-series anom- aly detection[C]//Proceedings of the AAAI Conference on Artificial Intelligence. 2022, 36(7): 7194-7201.
- Wang R, Mou X, Yang R, et al. CutAddPaste: Time Series Anomaly Detection by Exploiting Abnormal Knowledge[C]//Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. 2024: 3176-3187.
- Deng A, Hooi B. Graph neural network-based anomaly detection in multivariate time series[C]//Proceedings of the AAAI conference on artificial intelligence. 2021, 35(5): 4027-4035.
- Audibert J, Michiardi P, Guyard F, et al. Usad: Unsupervised anomaly detection on multivariate time series[C]//Proceedings of the 26th ACM SIGKDD international conference on knowledge discovery & data mining. 2020: 3395-3404.
Cited by
Sorted by citations
Seo, J. K., Lee, J., Kim, B., Shim, W., & Seo, J. T. (2025) · Electronics · doi:10.3390/electronics15010020 · Cited by 15 · see citing works
- Authors
- Song, Y., Huang, H., Wei, Q., Liu, L., & Wei, Z.
- Affiliations
- PLA Information Engineering University (CN)
- Zhengzhou University (CN)
- Venue
- Proceedings of the 2025 6th International Conference on Computer Information and Big Data Applications
- Publisher
- ACM
- Published
- 2025-03-14
- Pages
- 377-383
- OpenAlex
- W4413845269
- Cited by
- 1
- References
- 5
- Citations by year
- 2025: 1
- FWCI
- 0.95
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- International Conference on Computer Information and Big Data Applications (CIBDA) (publishedVersion, cc-by)
- 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
- time series anomaly detection, industrial control systems, mixup, Dirichlet distribution, noise injection, frequency shift, SWaT dataset, WADI dataset, critical infrastructure security
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
