Abstract
The rapid development of IoT networks emphasises the critical importance of robust security measures. Consequently, anomaly-based intrusion detection systems using machine learning techniques have garnered significant attention due to their ability to detect unseen attacks. This study introduces neural network approaches for network attack detection. We propose supervised learning approaches, combining Artificial Neural Networks (ANN) and 2D Convolutional Neural Networks (2D-CNN) to detect attacks on the IoT-23 dataset. We only consider packets that belong to IPv4 and one of the three protocols: TCP, UDP, or ICMP. The ANN and 2D-CNN have achieved the highest accuracy of 99.71% and 99.34% on the IoT-23 datasets, respectively. Furthermore, by looking at the packet level, the 2D-CNN models show an approximately 40% improvement in feature extraction time compared to ANN models. Our approach offers innovative solutions for network attack detection systems which can be mapped on the latest computing architectures, including CNN accelerators and FPGAs.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Al-Garadi, M.A., Mohamed, A., Al-Ali, A.K., Du, X., Ali, I., Guizani, M.: A survey of machine and deep learning methods for internet of things (IoT) security. IEEE Commun. Surv. Tutor. 22(3), 1646–1685 (2020)
Alani, M.M., Miri, A.: Towards an explainable universal feature set for IoT intrusion detection. Sensors 22(15), 5690 (2022)
Bhatia, R., Benno, S., Esteban, J., Lakshman, T., Grogan, J.: Unsupervised machine learning for network-centric anomaly detection in IoT. In: Proceedings of the 3rd ACM CoNEXT Workshop on Big Data, Machine Learning and Artificial Intelligence for Data Communication Networks, pp. 42–48 (2019)
Dutta, V., Choraś, M., Pawlicki, M., Kozik, R.: A deep learning ensemble for network anomaly and cyber-attack detection. Sensors 20(16), 4583 (2020)
Fahim, M., Sillitti, A.: Anomaly detection, analysis and prediction techniques in IoT environment: a systematic literature review. IEEE Access 7, 81664–81681 (2019)
Garcia, S., Parmisano, A., Erquiaga, M.: IoT-23: a labeled dataset with malicious and benign IoT network traffic. Stratosphere Lab., Praha, Czech Republic, Technical report (2020)
Hegde, M., Kepnang, G., Al Mazroei, M., Chavis, J.S., Watkins, L.: Identification of botnet activity in IoT network traffic using machine learning. In: 2020 International Conference on Intelligent Data Science Technologies and Applications (IDSTA), pp. 21–27. IEEE (2020)
Hussain, F., Abbas, S.G., Fayyaz, U.U., Shah, G.A., Toqeer, A., Ali, A.: Towards a universal features set for IoT botnet attacks detection. arXiv preprint arXiv:2012.00463 (2020)
Khan, A., Cotton, C.: Detecting attacks on IoT devices using featureless 1D-CNN. In: 2021 IEEE International Conference on Cyber Security and Resilience (CSR), pp. 461–466. IEEE (2021)
Lightbody, D., Ngo, D.M., Temko, A., Murphy, C.C., Popovici, E.: Attacks on IoT: side-channel power acquisition framework for intrusion detection. Future Internet 15(5), 187 (2023)
Ngo, D.M., et al.: HH-NIDS: heterogeneous hardware-based network intrusion detection framework for IoT security. Future Internet 15(1), 9 (2023)
Nobakht, M., Javidan, R., Pourebrahimi, A.: DEMD-IoT: a deep ensemble model for IoT malware detection using CNNs and network traffic. Evol. Syst. 1–17 (2022)
PyTorch Contributors: ADAM. https://pytorch.org/docs/stable/generated/torch.optim.Adam.html. Accessed 07 June 2023
Scott, H., Josh, F.: MTU size issues, fragmentation, and jumbo frames. https://www.networkworld.com/article/2224654/mtu-size-issues.html. Accessed 07 June 2023
Ullah, I., Mahmoud, Q.H.: Design and development of RNN anomaly detection model for IoT networks. IEEE Access 10, 62722–62750 (2022)
Vailshery, L.S.: Number of internet of things (IoT) connected devices worldwide from 2019 to 2030, by vertical. https://www.statista.com/statistics/1194682/iot-connected-devices-vertically/. Accessed 07 June 2023
Yang, Z., et al.: A systematic literature review of methods and datasets for anomaly-based network intrusion detection. Comput. Secur. 102675 (2022)
Acknowledgement
This research is supported in part by a grant from Science Foundation Ireland INSIGHT Centre for Data Analytics (Grant number 12/RC/2289-P2) which is co-funded under the European Regional Development Fund. The authors acknowledge the University College Cork (UCC) and Ho Chi Minh City University of Technology (HCMUT), VNU-HCM for supporting this study. We would like also to acknowledge the support from Qualcomm, Analog Devices, AMD/Xilinx and Dell for various parts of this project.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Ngo, DM. et al. (2023). Network Attack Detection on IoT Devices Using 2D-CNN Models. In: Dao, NN., Thinh, T.N., Nguyen, N.T. (eds) Intelligence of Things: Technologies and Applications. ICIT 2023. Lecture Notes on Data Engineering and Communications Technologies, vol 188. Springer, Cham. https://doi.org/10.1007/978-3-031-46749-3_23
Download citation
DOI: https://doi.org/10.1007/978-3-031-46749-3_23
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-46748-6
Online ISBN: 978-3-031-46749-3
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)