Abstract
Wireless sensor networks function as one of the enablers for the large-scale deployment of Internet of Things in various applications, including critical infrastructure. However, the open communications environment of wireless systems, immature technologies and the inherent limitations of sensor nodes make wireless sensor networks an attractive target to malicious activities. The main contributions of this review include describing the true nature of wireless sensor networks through their characteristics and security threats as well as reflecting them to network anomaly detection by surveying recent studies in the field. The potential and feasibility of graph-based deep learning for detecting anomalies in these networks are also explored. Finally, some remarks on modelling anomaly detection methods, using appropriate datasets for validation purposes and interpreting complex machine learning models are given.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
- 2.
Complexity may not also be stable: the amount of complexity can vary according to changes in the system, the environment or transmitted data.
- 3.
Research across a range of disciplines is devoted to finding linear approximations of nonlinear phenomena, because they are easier to solve.
- 4.
Especially the assumption of identically and independently distributed (i.i.d.) variables and presuming the density distribution of data points a priori may not be realistic.
- 5.
To overcome the limitations of traditional autoencoders, the study employes a sparse autoencoder and multiple denoising autoencoders for the sub-networks.
- 6.
In practical terms, there must not be a queue of packets awaiting to be processed by the model. Technically the packet processing rate must be higher than the expected maximum packet arrival rate.
- 7.
A detection scheme is expected to have the capability of addressing a wide range of security issues.
- 8.
Geometric deep learning is an umbrella term for emerging techniques, such as deep learning on graphs and manifolds, attempting to generalize deep neural models to non-Euclidean domains. For a comprehensive introductory-level reference with descriptive graphics and further details, see [22].
- 9.
The proposed method uses three hidden layers in the convolutional encoder, but the authors note that more layers can be stacked for building a deeper network.
- 10.
In general, spectral-based methods are computationally more expensive, assume a fixed input graph and are limited to work on undirected graphs whereas spatial-based methods can are more generalizable and can deal with directed graphs.
- 11.
Graph neural networks with attention mechanisms are an example of spatial-based approaches.
- 12.
Typically enhanced with LSTM or GRU.
- 13.
The authors use the GCN introduced in [25] and used in DOMINANT.
- 14.
The authors apply GRU but LSTM could be tested as well.
- 15.
- 16.
- 17.
References
Rawat, P., Singh, K.D., Chaouchi, H., Bonnin, J.M.: Wireless sensor networks: a survey on recent developments and potential synergies. J. Supercomput. 68(1), 1–48 (2014)
Xie, M., Han, S., Tian, B., Parvin, S.: Anomaly detection in wireless sensor networks: a survey. J. Netw. Comput. Appl. 34(1), 1302–1325 (2011)
Dargie, W., Poellabauer, C.: Fundamentals of Wireless Sensor Networks - Theory and Practice. Wiley Series on Wireless Communications and Mobile Computing (2010)
Zou, Y., Zhu, J., Wang, X., Hanzo, L.: A survey on wireless security: technical challenges, recent advances, and future trends. Proc. IEEE 104(9), 1727–1765 (2016). https://doi.org/10.1109/JPROC.2016.2558521
Tomić, I., McCann, J.: A survey of potential security issues in existing wireless sensor network protocols. IEEE Internet Things J. 4(6), 1910–1923 (2017)
Butun, I., Salvatore, D.M., Sankar, R.: A survey of intrusion detection systems in wireless sensor networks. IEEE Commun. Surv. Tutorials 16(1), 266–282 (2014). https://doi.org/10.1109/SURV.2013.050113.00191
Kumar, D.P., Amgoth, T., Annavarapu, C.S.R.: Machine learning algorithms for wireless sensor networks: a survey. Inf. Fusion 49(1), 1–25 (2019)
Sha, K., Wei, W., Yang, T.A., Wang, Z., Shi, W.: On security challenges and open issues in internet of things. Future Gener. Comput. Syst. 83(1), 326–337 (2018)
CSA. https://downloads.cloudsecurityalliance.org/whitepapers/Security_Guidance_for_Early_Adopters_of_the_Internet_of_Things.pdf. Accessed 3 Mar 2019
Mosenia, A., Jha, N.K.: A comprehensive study of security of internet-of-things. IEEE Trans. Emerg. Top. Comput. 5(4), 586–602 (2017)
Labatut, V., Ozgovde, A.: Topological measures for the analysis of wireless sensor networks. Procedia Comput. Sci. 10, 397–404 (2012). https://doi.org/10.1016/j.procs.2012.06.052
Akoglu, L., Tong, H., Koutra, D.: Graph based anomaly detection and description: a survey. Data Min. Knowl. Disc. 29(3), 626–688 (2015)
Rajasegarar, S., Leckie, C., Palaniswami, M.: Anomaly detection in wireless sensor networks. IEEE Wirel. Commun. 15(4), 34–40 (2008)
Ball, J.E., Anderson, D.T., Chan, C.S.: A comprehensive survey of deep learning in remote sensing: theories, tools and challenges for the community. J. Appl. Remote Sens. 11(4), 042609 (2017). https://doi.org/10.1117/1.JRS.11.042609
Liu, W., Wang, Z., Liu, X., Zeng, N., Liu, Y., Alsaadi, F.E.: A survey of deep neural network architectures and their applications. Neurocomputing 234(1), 11–26 (2017)
Chalapathy, R., Chawla, S.: Deep Learning for Anomaly Detection: A Survey (2019). A preprint. https://arxiv.org/abs/1901.03407. Accessed 3 May 2019
Ma, T., Wang, F., Cheng, J., Yu, Y., Chen, X.: A hybrid spectral clustering and deep neural network ensemble algorithm for intrusion detection in sensor networks. Sensors (Basel) 16(10), 1701 (2016). https://doi.org/10.3390/s16101701
Al-Hawawreh, M., Moustafa, N., Sitnikova, E.: Identification of malicious activities in industrial internet of things based on deep learning models. J. Inf. Secur. Appl. 41(1), 1–11 (2018)
Moustafa, N., Slay, J.: UNSW-NB15: a comprehensive data set for network intrusion detection systems (UNSW-NB15 network data set). In: Military Communications and Information Systems Conference (MilCIS) (2015). https://doi.org/10.1109/MilCIS.2015.7348942
Mirsky, Y., Doitshman, T., Elovici, Y., Shabtai, A.: Kitsune: an ensemble of autoencoders for online network intrusion detection. In: Network and Distributed Systems Security Symposium (NDSS) (2018). https://doi.org/10.14722/ndss.2018.23211
Hamilton, W.L., Ying, R., Leskovec, J.: Representation Learning on Graphs: Methods and Applications (2018). https://arxiv.org/abs/1709.05584. Accessed 3 Mar 2019
Bronstein, M.M., Bruna, J., LeCun, Y., Szlam, A., Vandergheynst, P.: Geometric deep learning: going beyond Euclidean data. IEEE Signal Process. Mag. 34(4), 18–42. IEEE (2017). https://doi.org/10.1109/MSP.2017.2693418
Xu, K., Wang, Z., Witbrock, M., Wu, L., Feng, Y., Sheinin, V.: Graph2Seq: Graph to Sequence Learning with Attention-based Neural Networks (2018). https://arxiv.org/abs/1804.00823. Accessed 3 May 2019
Ding, K., Li, J., Bhanushali, R., Liu, H.: Deep anomaly detection in attributed networks. In: SIAM International Conference on Data Mining (2019)
Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. In: Proceedings of the International Conference on Learning Representations (2017)
Wu, Z., Pan, S., Chen, F., Long, G., Zhang, C., Yu, P.S.: A Comprehensive Survey on Graph Neural Networks (2019). http://arxiv.org/abs/1901.00596. Accessed 4 May 2019
Monti, F., Otness, K., Bronstein, M.M.: MotifNet: a motif-based graph convolutional network for directed graphs. In: Data Science Workshop (DSW). IEEE (2018). https://doi.org/10.1109/DSW.2018.8439897
Wu, F., Fan, A., Baevski, A., Dauphin, Y.N., Auli, M.: Pay less attention with lightweight and dynamic convolutions (2019). https://arxiv.org/abs/1901.10430
O’Reilly, C., Gluhak, A., Imran, M.A., Rajasegarar, S.: Anomaly detection in wireless sensor networks in a non-stationary environment. IEEE Commun. Surv. Tutorials 16(3), 1413–1432 (2014)
Pareja, A., et al.: EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs (2019). https://arxiv.org/abs/1902.10191. Accessed 7 May 2019
Ranshous, S., Shen, S., Koutra, D., Harenberg, S., Faloutsos, C., Samatova, N.F.: Anomaly detection in dynamic networks: a survey. WIREs Comput. Stat. 7(3) (2015). https://doi.org/10.1002/wics.1347
Ding, K., Li, J., Liu, H.: Interactive anomaly detection in attributed networks. In: Proceedings of the Twelfth ACM International Conference on Web Search and Data Mining (WSDM 2019) (2019). https://doi.org/10.1145/3289600.3290964
Eswaran, D., Guha, S., Mishra, N.: SpotLogiht: detecting anomalies in streaming graphs. In: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (KDD 2018), pp. 1378–1386. ACM, New York (2018). https://doi.org/10.1145/3219819.3220040
Miz, V., Ricaud, B., Benzi, K., Vandergheynst, P.: Anomaly detection in the dynamics of web and social networks. (2019). https://arxiv.org/abs/1901.09688
Xue, L., Luo, M., Peng, Z., Li, J., Chen, Y., Liu, J.: Anomaly detection in time-evolving attributed networks. In: Database Systems for Advanced Applications (2019). https://doi.org/10.1007/978-3-030-18590-9_19
Yu, W., Cheng, W., Aggarwal, C.C., Chang, K., Chen, H., Wang, W.: NetWalk: a flexible deep embedding approach for anomaly detection in dynamic networks. In: In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (KDD 2018), pp. 2672–2681. ACM, New York (2018). https://doi.org/10.1145/3219819.3220024
Ahmad, S., Lavin, A., Purdy, S., Agha, Z.: Unsupervised real-time anomaly detection for streaming data. Neurocomputing 262(1), 134–147 (2017)
Cimini, G., Squartini, T., Saracco, F., Garlaschelli, D., Gabrielli, A., Galdarelli, G.: The Statistical Physics of Real-World Networks (2018). https://arxiv.org/abs/1810.05095
Bodström, T., Hämäläinen, T.: A novel deep learning stack for APT detection. MDPI Appl. Sci. 9(6), 1055 (2019)
Diverak, A., Parekh, M., Savla, V., Mishra, R.: Benchmarking datasets for anomaly-based network intrusion detection: KDD CUP 99 alternatives. In: 3rd International Conference on Computing, Communication and Security (ICCCS), pp. 1–8. IEEE (2018)
Ring, M., Wunderlich, S., Scheuring, D., Landes, D., Hotho, A.: A Survey of Network-based Intrusion Detection Data Sets (2019). https://arxiv.org/abs/1903.02460
Montavon, G., Samek, W., Müller, K.: Methods for interpreting and understanding deep neural networks. Digital Sig. Process. 73(1), 1–15 (2018)
Zhou, C., Paffenroth, R.C.: Anomaly detection with robust deep autoencoders. In: Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD 2017), pp. 665–674. ACM, New York (2018). https://doi.org/10.1145/3097983.3098052
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Leppänen, R.F., Hämäläinen, T. (2019). Network Anomaly Detection in Wireless Sensor Networks: A Review. In: Galinina, O., Andreev, S., Balandin, S., Koucheryavy, Y. (eds) Internet of Things, Smart Spaces, and Next Generation Networks and Systems. NEW2AN ruSMART 2019 2019. Lecture Notes in Computer Science(), vol 11660. Springer, Cham. https://doi.org/10.1007/978-3-030-30859-9_17
Download citation
DOI: https://doi.org/10.1007/978-3-030-30859-9_17
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-30858-2
Online ISBN: 978-3-030-30859-9
eBook Packages: Computer ScienceComputer Science (R0)