Abstract
Cyber-Physical Systems (CPSs) integrate sensing, computation, cybernetics, and networking to control a hybrid physical system consisting of different functional subsystems. Accurate and efficient anomaly detection for Multivariate Time Series (MTS) with rich temporal and spatial information generated by highly intertwined sensors and actuators in CPS to reduce the negative influence caused by abnormalities. Since existing methods with temporal modeling cannot effectively recognize anomalies without sufficiently utilizing spatial correlations conveyed by MTS data, Graph Convolution Networks (GCNs) have recently been exploited to extract spatial correlations in MTS data. However, most previous works that utilized spatial information focused on learning static long-term graph structures and did not explore the potential variations of short-term spatial correlations. This paper proposed a Multivariate Anomaly Detection framework with multi-scale Self-learned Graph Structures (MAD-SGS) based on the Variational Autoencoder (VAE) architecture. Specifically, the Long Short-Term Memory (LSTM) was applied to extract and exploit the temporal information, and the Graph Convolution Network (GCN) was employed to exploit spatial correlations at different scales (the long-term static correlation and short-term dynamic correlation). Besides, we utilized a self-learning approach for long-term graph static structure learning and employed feature similarity to learn short-term dynamic graph structures. The proposed MAD-SGS framework was tested on four datasets collected from three real-world CPSs: the Secure Water Treatment (SWaT), the Water Distribution (WADI), and the BATtle of Attack Detection Algorithm (BATADAL) datasets. Experimental results indicated that the proposed MAD-SGS outperformed the state-of-the-art methods.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Ahmed, C.M., Zhou, J., Mathur, A.P.: Noise matters: using sensor and process noise fingerprint to detect stealthy cyber attacks and authenticate sensors in cps. In: Proceedings of the 34th Annual Computer Security Applications Conference, pp. 566–581 (2018)
Audibert, J., Michiardi, P., Guyard, F., Marti, S., Zuluaga, M.A.: USAD: unsupervised anomaly detection on multivariate time series. In: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 3395–3404 (2020)
Bogaerts, T., Masegosa, A.D., Angarita-Zapata, J.S., Onieva, E., Hellinckx, P.: A graph CNN-LSTM neural network for short and long-term traffic forecasting based on trajectory data. Transp. Res. Part C: Emerg. Technol. 112, 62–77 (2020)
Breunig, M.M., Kriegel, H.P., Ng, R.T., Sander, J.: LOF: identifying density-based local outliers. In: Proceedings of the 2000 ACM SIGMOD International Conference on Management of Data, pp. 93–104 (2000)
Deng, A., Hooi, B.: Graph neural network-based anomaly detection in multivariate time series. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 4027–4035 (2021)
Diao, Z., Wang, X., Zhang, D., Liu, Y., Xie, K., He, S.: Dynamic spatial-temporal graph convolutional neural networks for traffic forecasting. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 890–897 (2019)
Garg, A., Zhang, W., Samaran, J., Savitha, R., Foo, C.S.: An evaluation of anomaly detection and diagnosis in multivariate time series. IEEE Trans. Neural Netw. Learn. Syst. 33(6), 2508–2517 (2021)
He, Y., Zhao, J.: Temporal convolutional networks for anomaly detection in time series. J. Phys: Conf. Ser. 1213(4), 42050 (2019)
Huang, T., Liu, C., Sharma, A., Sarkar, S.: Traffic system anomaly detection using spatiotemporal pattern networks. Int. J. Prognost. Health Manage. 9(1) (2018)
Li, D., Chen, D., Jin, B., Shi, L., Goh, J., Ng, S.-K.: MAD-GAN: multivariate anomaly detection for time series data with generative adversarial networks. In: Tetko, I.V., Kůrková, V., Karpov, P., Theis, F. (eds.) ICANN 2019, Part IV. LNCS, vol. 11730, pp. 703–716. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-30490-4_56
Li, D., Hu, G., Spanos, C.J.: A data-driven strategy for detection and diagnosis of building chiller faults using linear discriminant analysis. Energy Build. 128, 519–529 (2016)
Li, D., Zhou, Y., Hu, G., Spanos, C.J.: Fault detection and diagnosis for building cooling system with a tree-structured learning method. Energy Build. 127, 540–551 (2016)
Li, Z.L., Zhang, G.W., Yu, J., Xu, L.Y.: Dynamic graph structure learning for multivariate time series forecasting. Pattern Recogn. 138, 109423 (2023)
Liu, F.T., Ting, K.M., Zhou, Z.H.: Isolation forest. In: 2008 Eighth IEEE International Conference on Data Mining, pp. 413–422. IEEE (2008)
Malhotra, P., Ramakrishnan, A., Anand, G., Vig, L., Agarwal, P., Shroff, G.: LSTM-based encoder-decoder for multi-sensor anomaly detection. arXiv preprint arXiv:1607.00148 (2016)
Mathur, A.P., Tippenhauer, N.O.: SWaT: a water treatment testbed for research and training on ICS security. In: 2016 International Workshop on Cyber-Physical Systems for Smart Water Networks (CySWater), pp. 31–36. IEEE (2016)
Miele, E.S., Bonacina, F., Corsini, A.: Deep anomaly detection in horizontal axis wind turbines using graph convolutional autoencoders for multivariate time series. Energy AI 8, 100145 (2022)
Perales Gómez, Á.L., Fernández Maimó, L., Huertas Celdrán, A., García Clemente, F.J.: MADICS: a methodology for anomaly detection in industrial control systems. Symmetry 12(10), 1583 (2020)
Qi, P., Li, D., Ng, S.K.: MAD-SGCN: multivariate anomaly detection with self-learning graph convolutional networks. In: 2022 IEEE 38th International Conference on Data Engineering (ICDE), pp. 1232–1244. IEEE (2022)
Scholkopf, B., Platt, J.C., Shawe-Taylor, J., Smola, A.J., Williamson, R.C.: Estimating the support of a high-dimensional distribution. Neural Comput. 13(7), 1443–1471 (2001)
Taormina, R., et al.: Battle of the attack detection algorithms: disclosing cyber attacks on water distribution networks. J. Water Resour. Plan. Manag. 144(8), 04018048 (2018)
Yang, J., Yue, Z.: Learning hierarchical spatial-temporal graph representations for robust multivariate industrial anomaly detection. IEEE Trans. Industr. Inform. (2022)
Zhang, J., Pan, L., Han, Q.L., Chen, C., Wen, S., Xiang, Y.: Deep learning based attack detection for cyber-physical system cybersecurity: a survey. IEEE/CAA J. Autom. Sinica 9(3), 377–391 (2021)
Zhao, H., et al.: Multivariate time-series anomaly detection via graph attention network. In: 2020 IEEE International Conference on Data Mining (ICDM), pp. 841–850. IEEE (2020)
Zhao, J., Wang, X., Shi, C., Hu, B., Song, G., Ye, Y.: Heterogeneous graph structure learning for graph neural networks. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 4697–4705 (2021)
Zong, B., et al.: Deep autoencoding gaussian mixture model for unsupervised anomaly detection. In: International Conference on Learning Representations (2018)
Acknowledgment
This research was supported by the Guangdong Basic and Applied Basic Research Foundation (2022A1515011713).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Tang, J., Li, D., Zheng, Z. (2024). MAD-SGS: Multivariate Anomaly Detection with Multi-scale Self-learned Graph Structures. In: Pan, L., Wang, Y., Lin, J. (eds) Bio-Inspired Computing: Theories and Applications. BIC-TA 2023. Communications in Computer and Information Science, vol 2062. Springer, Singapore. https://doi.org/10.1007/978-981-97-2275-4_2
Download citation
DOI: https://doi.org/10.1007/978-981-97-2275-4_2
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-97-2274-7
Online ISBN: 978-981-97-2275-4
eBook Packages: Computer ScienceComputer Science (R0)