BLS-identification: A device fingerprint classification mechanism based on broad learning for Internet of Things

Abstract

The popularity of the Internet of Things (IoT) has enabled a large number of vulnerable devices to connect to the Internet, bringing huge security risks. As a network-level security authentication method, device fingerprint based on machine learning has attracted considerable attention because it can detect vulnerable devices in complex and heterogeneous access phases. However, flexible and diversified IoT devices with limited resources increase difficulty of the device fingerprint authentication method executed in IoT, because it needs to retrain the model network to deal with incremental features or types. To address this problem, a device fingerprinting mechanism based on a Broad Learning System (BLS) is proposed in this paper. The mechanism firstly characterizes IoT devices by traffic analysis based on the identifiable differences of the traffic data of IoT devices, and extracts feature parameters of the traffic packets. A hierarchical hybrid sampling method is designed at the preprocessing phase to improve the imbalanced data distribution and reconstruct the fingerprint dataset. The complexity of the dataset is reduced using Principal Component Analysis (PCA) and the device type is identified by training weights using BLS. The experimental results show that the proposed method can achieve state-of-the-art accuracy and spend less training time than other existing methods.

Keywords

Device fingerprint / Traffic analysis / Class imbalance / Broad learning system / Access authentication

References

[1] IoT connections outlook. https://www.ericsson.com/en/mobility-report/dataforecasts/iot-connections-outlook/, 2021 (accessed 13 Oct. 2021).

[2] Y. Li, B. Cao, M. Peng, L. Zhang, L. Zhang, D. Feng, J. Yu, Direct acyclic graph-based ledger for internet of things: performance and security analysis, IEEE/ACM Trans. Netw. 28 (4) (2020) 1643-1656.

[3] C. Yang, L. Min, L. Qun, Access authentication method for IoT terminal devices based on deep learning, Netinfo Security 20 (11) (2020) 67-74.

[4] P. Sanchez, J. Valero, A.H. Celdran, G. Bovet, G.M. Perez, A survey on device behavior fingerprinting: data sources, techniques, application scenarios, and datasets, IEEE.Commun. Surv. Tutorials 23 (2) (2021) 1048-1077.

[5] H.H. Gharakheili, A. Sivanathan, A. Hamza, V. Sivaraman, Network-level security for the internet of things: opportunities and challenges, Computer 52 (8) (2019) 58-62.

[6] A. Sivanathan, D. Sherratt, H.H. Gharakheili, V. Sivaraman, A. Vishwanath, Low-cost flow-based security solutions for smart-home IoT devices, in: IEEE Advanced Networks and Telecommunications Systems (ANTS), IEEE, 2016, pp. 1-7.

[7] R.C. E, Y. Chao, S. Yanli, L. Zhulin, C.L.P. Chen, Research of broad learning system, Appl. Res. Comput. 38 (8) (2021) 1-12.

[8] B. Cao, Y. Li, L. Zhang, L. Zhang, S. Mumtaz, Z. Zhou, M. Peng, When internet of things meets blockchain: challenges in distributed consensus, IEEE Network 33 (6)(2019) 133-139.

[9] B. Cao, L. Zhang, Y. Li, D. Feng, W. Cao, Intelligent offloading in multi-access edge computing: a state-of-the-art review and framework, IEEE Commun. Mag. 57 (3)(2019) 56-62.

[10] B. Cao, S. Xia, J. Han, Y. Li, A distributed game methodology for crowdsensing in uncertain wireless scenario, IEEE Trans. Mobile Comput. 19 (1) (2019) 15-28.

[11] B. Cao, Z. Zhang, D. Feng, S. Zhang, L. Zhang, M. Peng, Y. Li, Performance analysis and comparison of pow, pos and dag based blockchains, Digit.Commun. Network 6 (4) (2020) 480-485.

[12] L. Zhang, B. Cao, Y. Li, M. Peng, G. Feng, A multi-stage stochastic programming-based offloading policy for fog enabled iot-ehealth, IEEE J. Sel. Area. Commun. 39 (2) (2020) 411-425.

[13] S.V. Radhakrishnan, A.S. Uluagac, R. Beyah, Gtid: a technique for physical device and device type fingerprinting, IEEE Trans. Dependable Secure Comput. 12 (5) (2014) 519-532.

[14] K. Gao, C. Corbett, R. Beyah, A passive approach to wireless device fingerprinting, in: 2010 IEEE/IFIP International Conference on Dependable Systems & Networks (DSN), IEEE, 2010, pp. 383-392.

[15] A. Sivanathan, H.H. Gharakheili, V. Sivaraman, Can we classify an iot device using tcp port scan?, in: 2018 IEEE International Conference on Information and Automation for Sustainability (ICIAS) IEEE, 2018, pp. 1-4.

[16] A. Sivanathan, H.H. Gharakheili, V. Sivaraman, Managing IoT cyber-security using programmable telemetry and machine learning, IEEE.Trans.Netw.Serv. Manag. 17 (1) (2020) 60-74.

[17] H. Zhao, J. Zheng, J. Xu, W. Deng, Fault diagnosis method based on principal component analysis and broad learning system, IEEE Access 7 (8) (2019) 99263-99272.

[18] R. Han, R. Wang, G. Zeng, Fault diagnosis method of power electronic converter based on broad learning, Complexity 2020 (11) (2020) 1-9.

[19] H.G. Han, F.F. Yang, H.Y. Yang, X.L. Wu, Type-2 fuzzy broad learning controller for wastewater treatment process, Neurocomputing 459 (2021) 188-200.

[20] S.B. Jie, C.X. Peng, M.Y. Zhe, G.L. Long, MSE_bls: abnormal traffic detection method based on broad learning system, J. Inf.Eng.Univ. 21 (2) (2020) 1-5.

[21] Y.Y. Jiao, Q. Yu, Z.L. Chao, An anomaly detection approach on servers trafficin smart grid based on breadth learning algorithm, Comput. Mod. 3 (9) (2019) 1-7.

[22] X. Zhu, T. Qiu, W. Qu, X. Zhou, M. Atiquzzaman, D. Wu, Bls-location: a wireless fingerprint localization algorithm based on broad learning, IEEE Trans. Mobile Comput. (1) (2021) 1-14.

[23] A. Sivanathan, D. Sherratt, H.H. Gharakheili, A. Radford, C. Wijenayake, A. Vishwanath, V. Sivaraman, Characterizing and classifying iot traffic in smart cities and campuses, in: 2017 IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS), IEEE, 2017, pp. 559-564.

[24] M. Miettinen, S. Marchal, I. Hafeez, T. Frassetto, N. Asokan, A.R. Sadeghi, S. Tarkoma, IoT SENTINEL: automated device-type identification for security enforcement in IoT, in: 2017 IEEE 37th International Conference on Distributed Computing Systems (ICDCS), IEEE, 2017, pp. 2177-2184.

[25] W.C. Yang, Y.B. Guo, T. Li, B.Q. Zhu, Method based on traffic fingerprint for IoT device identification and IoT security model, Computer Science 47 (7) (2020) 299-306.

[26] F. Rayhan, S. Ahmed, A. Mahbub, R. Jani, S. Shatabda, D.M. Farid, Cusboost: cluster-based under-sampling with boosting for imbalanced classification, in: 2017 2nd International Conference on Computational Systems and Information Technology for Sustainable Solution (CSITSS), IEEE, 2017, pp. 1-5.

[27] J. Fonseca, G. Douzas, F. Bacao, Improving imbalanced land cover classification with k-means smote: detecting and oversampling distinctive minority spectral signatures, Information 12 (7) (2021) 1-20.

[28] Q. Kang, L. Shi, M. Zhou, X. Wang, Q. Wu, Z. Wei, A distance-based weighted undersampling scheme for support vector machines and its application to imbalanced classification, IEEE Transact. Neural Networks Learn. Syst. 29 (9) (2017) 4152-4165.

[29] G.E. Hinton, R.R. Salakhutdinov, Reducing the dimensionality of data with neural networks, Science 313 (5786) (2006) 504-507.

[30] C.P. Chen, Z. Liu, Broad learning system: an effective and efficient incremental learning system without the need for deep architecture, IEEE Transact. Neural Networks Learn. Syst. 29 (1) (2017) 10-24.

[31] C.P. Chen, Z. Liu, Broad learning system: a new learning paradigm and system without going deep, in: 2017 32nd Youth Academic Annual Conference of Chinese Association of Automation (YAC), IEEE, 2017, pp. 1271-1276.

[32] C.P. Chen, Z. Liu, S. Feng, Universal approximation capability of broad learning system and its structural variations, IEEE Transact. Neural Networks Learn. Syst. 30 (4) (2018) 1191-1204.

[33] R.G. Li, P.Y. Duan, M. Shen, L.H. Zhu, Traffic classification algorithm of internet of things based on random forest, J. Beijing Univ. Aeronaut. Astronaut. 48 (2) (2022) 233-239.