ConnectNet with Graph-Based Transformers: a New Deep Learning Approach for Detecting Intrusions in Industrial IoT Networks
Main Article Content
Abstract
Intrusion detection systems (IDSs) are now widely used in conjunction with Industrial Internet of Things (IIoT) systems to mitigate security threats, but they often lead to too many false alarms detected. This research proposes a deep learning approach based on pretraining of deep neural networks and deep autoencoders which improves attack prediction accuracy and reduces false positives. The model performance is then improved through hyperparameter optimization. Instead of using common deep learning architectures, this work proposes CNetGT. ConnectNet is a new approach using Graph-based Transformer architecture and allows effective detection. CNetGT detects which features are the most beneficial and which categorical hyperparameters give the best combination of results. CNetGT has been tested using DS2OS dataset and evaluated with various metrics. Its performance is then benchmarked against a number of existing attack-detection techniques, and the comparison shows that CNetGT consistently comes out ahead. Overall, the proposed security framework is effective at cutting down both internal and external threats, reaching 98.6% accuracy, 98.2% precision, 97% recall, a 98.4% F1-score, and a 98.5% intrusion detection rate (IDR).
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
References
S. Garcia, A. Parmisano, and M. J. Erquiaga, "A labeled dataset with malicious and benign IoT network traffic," 2020. [Online]. Available: https://www.stratosphereips.org/datasets-iot23
Y. Gao, Y. Liu, Y. Jin, J. Chen, and H. Wu, "A novel semi-supervised learning approach for network intrusion detection on cloud-based robotic system," IEEE Access, vol. 6, pp. 50927-50938, 2018.
T. Tang, L. Mhamdi, D. McLernon, S. A. R. Zaidi, and M. Ghogho, "Deep learning approach for network intrusion detection in software defined networking," in Proc. Int. Conf. Wireless Netw. Mobile Commun. (WINCOM), 2016, pp. 258-263.
W. Zhong, N. Yu, and C. Ai, "Applying big data based deep learning system to intrusion detection," Big Data Min. Anal., vol. 3, no. 3, pp. 181-195, Sep. 2020.
A. Haghighat and J. Li, "Intrusion detection system using voting-based neural network," Tsinghua Sci. Technol., vol. 26, no. 4, pp. 484-495, Aug. 2021.
L. Yang et al., "ASTREAM: Data-stream-driven scalable anomaly detection with accuracy guarantee in IIoT environment," IEEE Trans. Netw. Sci. Eng., early access, Mar. 8, 2022.
X. Zhang et al., "LSHiForest: A generic framework for fast tree isolation based ensemble anomaly analysis," in Proc. IEEE 33rd Int. Conf. Data Eng. (ICDE), Apr. 2017, pp. 983-994.
L. Qi, Y. Yang, X. Zhou, W. Rafique, and J. Ma, "Fast anomaly identification based on multi-aspect data streams for intelligent intrusion detection toward secure industry 4.0," IEEE Trans. Ind. Informat., vol. 18, no. 9, pp. 6503-6511, Sep. 2022.
C. Yin, Y. Zhu, J. Fei, and X. He, "A deep learning approach for intrusion detection using recurrent neural networks," IEEE Access, vol. 5, pp. 21954-21961, 2017.
C. Xu, J. Shen, X. Du, and F. Zhang, "An intrusion detection system using a deep neural network with gated recurrent units," IEEE Access, vol. 6, pp. 48697-48707, 2018.
J. Gao et al., "OmniSCADA intrusion detection using deep learning algorithms," IEEE Internet Things J., vol. 8, no. 2, pp. 951-961, Jan. 2021.
B. Yan and G. Han, "Effective feature extraction via stacked sparse autoencoder to improve intrusion detection system," IEEE Access, vol. 6, pp. 41238-41248, 2018.
C. Ieracitano, A. Adeel, F. C. Morabito, and A. Hussain, "A novel statistical analysis and autoencoder driven intelligent intrusion detection approach," Neurocomputing, vol. 387, pp. 51-62, Apr. 2020.
S. Shahriar, N. I. Haque, M. A. Rahman, and M. Alonso, "G-IDS: Generative adversarial networks assisted intrusion detection system," in Proc. IEEE 44th Annu. Comput., Softw., Appl. Conf. (COMPSAC), Jul. 2020, pp. 376-385.
I. Yilmaz, R. Masum, and A. Siraj, "Addressing imbalanced data problem with generative adversarial network for intrusion detection," in Proc. IEEE 21st Int. Conf. Inf. Reuse Integr. Data Sci. (IRI), Las Vegas, NV, USA, 2020, pp. 25-30.
J. Lee, B. Noh, Y. Kim, and K. Jeong, "Generation of network traffic using WGAN-GP and a DFT filter for resolving data imbalance," in Proc. Int. Conf. Internet Distrib. Comput. Syst. (IDCS), Oct. 2019, pp. 306-317.
S. Dlamini and M. Fahim, "DGM: A data generative model to improve minority class presence in anomaly detection domain," Neural Comput. Appl., vol. 33, pp. 13635-13646, Apr. 2021.
S. Alabugin and A. N. Sokolov, "Applying of generative adversarial networks for anomaly detection in industrial control systems," in Proc. Global Smart Ind. Conf. (GloSIC), Nov. 2020, pp. 199-203.
I. Siniosoglou, P. Radoglou-Grammatikis, G. Efstathopoulos, P. Fouliras, and P. Sarigiannidis, "A unified deep learning anomaly detection and classification approach for smart grid environments," IEEE Trans. Netw. Service Manage., vol. 18, no. 2, pp. 1137-1151, Jun. 2021.
M. Arjovsky, S. Chintala, and L. Bottou, "Wasserstein generative adversarial networks," in Proc. 34th Int. Conf. Mach. Learn. (ICML), 2017, pp. 214-223.
S. Lee, J. Kim, I. Kim, and K. Han, "Cyber threat detection based on artificial neural networks using event profiles," IEEE Access, vol. 7, pp. 165607-165626, 2019.
P. Sun, P. Liu, Q. Li, C. Liu, X. Lu, R. Hao, and J. Chen, "DL-IDS: Extracting features using CNN-LSTM hybrid network for intrusion detection system," Secur. Commun. Netw., vol. 2020, Aug. 2020, Art. no. 8890306.
S. Alkahtani and T. H. H. Aldhyani, "Intrusion detection system to advance Internet of Things infrastructure-based deep learning algorithms," Complexity, vol. 2021, Jul. 2021, Art. no. 5579851.
H. Benmeziane, "Comparison of deep learning frameworks and compilers," M.S. thesis, Dept. Comput. Sci., Ecole Nationale Superieure d'Informatique, Oued Smar, Algeria, 2020.
A. Halbouni, T. S. Gunawan, M. H. Habaebi, M. Halbouni, M. Kartiwi, and R. Ahmad, "Machine learning and deep learning approaches for cybersecurity: A review," IEEE Access, vol. 10, pp. 19572-19585, 2022.
I. Almomani, B. Al-Kasasbeh, and M. Al-Akhras, "WSN-DS: A dataset for intrusion detection systems in wireless sensor networks," J. Sensors, vol. 2016, Aug. 2016, Art. no. 4731953.
F. Rustam, K. Ramli, N. Hayati, E. Ihsanto, T. S. Gunawan, and A. H. Halbouni, "Development of intrusion detection system using residual feed forward neural network algorithm," in Proc. 4th Int. Seminar Res. Inf. Technol. Intell. Syst. (ISRITI), Dec. 2021, pp. 539-543.
Y. Lei, N. Li, S. Gontarz, J. Lin, S. Radkowski, and J. Dybala, "A model-based method for remaining useful life prediction of machinery," IEEE Transactions on Reliability, vol. 65, no. 3, pp. 1314-1326, 2016.
H. Shao, W.-J. Sun, R.-Q. Yan, P. Wang, and R. X. Gao, "A deep learning approach for fault diagnosis of induction motors in manufacturing," Chinese Journal of Mechanical Engineering, vol. 30, no. 6, pp. 1347-1356, 2017.
C. Sun, N. Wang, X. Li, and W. Zhang, "Remaining useful life prediction for a machine with multiple dependent features based on Bayesian dynamic linear model and copulas," IEEE Access, vol. 5, pp. 16277-16287, 2017