An attention mechanism based recurrent neural network with dimensionality reduction model for cyber threat detection in IoT environment

Randa Allafi; Randa Allafi

doi:10.3934/math.2025544

AIMS Mathematics

2025, Volume 10, Issue 5: 11998-12031. doi: 10.3934/math.2025544

Previous Article Next Article

Research article Special Issues

An attention mechanism based recurrent neural network with dimensionality reduction model for cyber threat detection in IoT environment

Randa Allafi ^,

Department of Computer Science, College of Science, Northern Border University, Arar, Saudi Arabia

Received: 02 February 2025 Revised: 13 April 2025 Accepted: 22 April 2025 Published: 23 May 2025
MSC : 00A69

Besides the developing threat of cyberattacks, cybersecurity is one of the most significant Internet of Things (IoT) regions. While the IoT has formed a novel model where a network of devices and machines is efficient in collaborating and communicating with each other, it is a novel process invention in enterprises. The role of cybersecurity is to mitigate risks for institutions and users by safeguarding data confidentiality across networks. The growing tools and technologies for cybersecurity improve safety in IoT systems. AI is helpful in improving cybersecurity by providing real-time information for faster threat detection, rapid responses, and smarter decisions. Moreover, integrating blockchain (BC) with IoT illustrates promise but encounters threats like performance issues, security vulnerabilities, and scalability limits. Still, BC plays a key part in protecting low-energy IoT devices. In this study, I proposed a novel approach using an Attention Mechanism-Based Recurrent Neural Network and Dimensionality Reduction for Cyber Threat Detection (AMRNN-DRCTD) model. The main goal of the proposed AMRNN-DRCTD model was to enhance the detection system for cyberattacks in IoT networks. I considered possible security breaches in BC and their influence on network processes. At the initial stage, the data normalization applied zero-mean normalization to alter data into a consistent setup. The feature selection process employed the chaotic and terminal strategy-based butterfly optimization algorithm (CTBOA). Furthermore, the proposed AMRNN-DRCTD model utilized the hybrid convolutional neural network and bi-directional long short-term memory with an attention mechanism (CNN-BiLSTM-AM) technique for the classification process. Finally, the Honey Badger Algorithm (HBA)-based hyperparameter selection range was accomplished to optimize the detection outcomes of the CNN-BiLSTM-AM technique. The experimental evaluation of the AMRNN-DRCTD methodology was examined under the BoT-IoT dataset. The performance validation of the AMRNN-DRCTD methodology highlighted a superior accuracy output of 99.28% over existing approaches.
- cyber threat detection,
- IoT,
- honey badger algorithm,
- recurrent neural network,
- attention mechanism,
- blockchain
Citation: Randa Allafi. An attention mechanism based recurrent neural network with dimensionality reduction model for cyber threat detection in IoT environment[J]. AIMS Mathematics, 2025, 10(5): 11998-12031. doi: 10.3934/math.2025544

Related Papers:

Abstract

Besides the developing threat of cyberattacks, cybersecurity is one of the most significant Internet of Things (IoT) regions. While the IoT has formed a novel model where a network of devices and machines is efficient in collaborating and communicating with each other, it is a novel process invention in enterprises. The role of cybersecurity is to mitigate risks for institutions and users by safeguarding data confidentiality across networks. The growing tools and technologies for cybersecurity improve safety in IoT systems. AI is helpful in improving cybersecurity by providing real-time information for faster threat detection, rapid responses, and smarter decisions. Moreover, integrating blockchain (BC) with IoT illustrates promise but encounters threats like performance issues, security vulnerabilities, and scalability limits. Still, BC plays a key part in protecting low-energy IoT devices. In this study, I proposed a novel approach using an Attention Mechanism-Based Recurrent Neural Network and Dimensionality Reduction for Cyber Threat Detection (AMRNN-DRCTD) model. The main goal of the proposed AMRNN-DRCTD model was to enhance the detection system for cyberattacks in IoT networks. I considered possible security breaches in BC and their influence on network processes. At the initial stage, the data normalization applied zero-mean normalization to alter data into a consistent setup. The feature selection process employed the chaotic and terminal strategy-based butterfly optimization algorithm (CTBOA). Furthermore, the proposed AMRNN-DRCTD model utilized the hybrid convolutional neural network and bi-directional long short-term memory with an attention mechanism (CNN-BiLSTM-AM) technique for the classification process. Finally, the Honey Badger Algorithm (HBA)-based hyperparameter selection range was accomplished to optimize the detection outcomes of the CNN-BiLSTM-AM technique. The experimental evaluation of the AMRNN-DRCTD methodology was examined under the BoT-IoT dataset. The performance validation of the AMRNN-DRCTD methodology highlighted a superior accuracy output of 99.28% over existing approaches.

References

[1]	S. Mishra, The impact of AI-based cyber security on the banking and financial sectors, J. Cybersecurity Inform. Manage., 14 (2024). https://doi.org/10.54216/JCIM.140101 doi: 10.54216/JCIM.140101
[2]	S. F. Rabooki, B. Li, F. G. Febrinanto, C. Peng, E. Naghizade, F. Han, et al., GraphDART: Graph distillation for efficient advanced persistent threat detection, arXiv preprin, 2025. https://doi.org/10.48550/arXiv.2501.02796
[3]	Y. M. Tashtoush, D. A. Darweesh, G. Husari, O. A. Darwish, Y. Darwish, L. B. Issa, et al, Agile approaches for cybersecurity systems, IoT, and intelligent transportation, IEEE Access, 10 (2021), 1360−1375. https://doi.org/10.1109/ACCESS.2021.3136861 doi: 10.1109/ACCESS.2021.3136861
[4]	A. Abdullah, R. Hamad, M. Abdulrahman, H. Moala, S. Elkhediri, CyberSecurity: A review of internet of things (IoT) security issues, challenges and techniques, In: 2019 2nd International Conference on Computer Applications & Information Security (ICCAIS), IEEE, 2019, 1−6. https://doi.org/10.1109/CAIS.2019.8769560
[5]	M. Roopak, G. Y. Tian, J. Chambers, Deep learning models for cyber security in IoT networks, In: 2019 IEEE 9th annual computing and communication workshop and conference (CCWC), IEEE, 2019. https://doi.org/10.1109/CCWC.2019.8666588
[6]	R. O. Andrade, S. G. Yoo, L. Tello-Oquendo, I. Ortiz-Garcés, A comprehensive study of the IoT cybersecurity in smart cities, IEEE Access, 8 (2020), 228922−228941. https://doi.org/10.1109/ACCESS.2020.3046442 doi: 10.1109/ACCESS.2020.3046442
[7]	M. Kuzlu, C. Fair, O. Guler, Role of artificial intelligence in the Internet of Things (IoT) cybersecurity, DIOT, 1 (2021), 7. https://doi.org/10.1007/s43926-020-00001-4 doi: 10.1007/s43926-020-00001-4
[8]	K. Kimani, V. Oduol, K. Langat, Cyber security challenges for IoT-based smart grid networks, Int. J. Crit. Infr. Prot., 25 (2019), 36−49. https://doi.org/10.1016/j.ijcip.2019.01.001 doi: 10.1016/j.ijcip.2019.01.001
[9]	I. Lee, Internet of Things (IoT) cybersecurity: Literature review and IoT cyber risk management, Future Internet, 12 (2020), 157. https://doi.org/10.3390/fi12090157 doi: 10.3390/fi12090157
[10]	A. Maseleno, Design of optimal machine learning based cybersecurity intrusion detection systems, J. Cybersecurity Inform. Manage., 1 (2019).
[11]	E. Gelenbe, M. Nakip, IoT network cybersecurity assessment with the associated random neural network, IEEE Access, 2023. https://doi.org/10.1109/ACCESS.2023.3297977 doi: 10.1109/ACCESS.2023.3297977
[12]	D. M. Mirzaaxmedov, Cybersecurity risk analysis in the IoT: A systematic review, Econ. Soc., 7 (2024), 145−151.
[13]	H. Zeng, M. Yunis, A. Khalil, N. Mirza, Towards a conceptual framework for AI-driven anomaly detection in smart city IoT networks for enhanced cybersecurity, J. Innov. Knowl., 9 (2024), 100601. https://doi.org/10.1016/j.jik.2024.100601 doi: 10.1016/j.jik.2024.100601
[14]	P. Kaliyaperumal, S. Periyasamy, M. Thirumalaisamy, B. Balusamy, F. Benedetto, A novel hybrid unsupervised learning approach for enhanced cybersecurity in the IoT, Future Internet, 16 (2024), 253. https://doi.org/10.3390/fi16070253 doi: 10.3390/fi16070253
[15]	A. L. Yakubu, Cybersecurity in the Internet of Things: Securing the connected world, Fac. Nat. Appl. Sci. J. Comput. Appl., 2 (2024), 100−104.
[16]	D. R. N. Pitty, V. Jain, M. Tamilselvam, D. Haripriya, S. Bansal, Cybersecurity challenges in the era of the Internet of Things (IoT): Developing robust frameworks for securing connected devices, Libr. Prog. Int., 44 (2024), 5644−5653.
[17]	A. Adewuyi, A. A. Oladele, P. U. Enyiorji, O. O. Ajayi, T. E. Tsambatare, K. Oloke, et al., The convergence of cybersecurity, Internet of Things (IoT), and data analytics: Safeguarding smart ecosystems, World J. Adv. Res. Rev., 23 (2024), 379−394. https://doi.org/10.30574/wjarr.2024.23.1.1993 doi: 10.30574/wjarr.2024.23.1.1993
[18]	K. S. Prasad, E. L. Lydia, M. V. Rajesh, K. Radhika, J. V. N. Ramesh, N. Neelima, et al., Augmenting cybersecurity through attention based stacked autoencoder with optimization algorithm for detection and mitigation of attacks on IoT assisted networks, Sci. Rep., 14 (2024), 30833. https://doi.org/10.1038/s41598-024-81162-y doi: 10.1038/s41598-024-81162-y
[19]	S. Markkandeyan, A. D. Ananth, M. Rajakumaran, R. G. Gokila, R. Venkatesan, B. Lakshmi, Novel hybrid deep learning based cyber security threat detection model with optimization algorithm, Cyber Secur. Appl., 3 (2025), 100075. https://doi.org/10.1016/j.csa.2024.100075 doi: 10.1016/j.csa.2024.100075
[20]	D. M. Dhanvijay, M. M. Dhanvijay, V. H. Kamble, Cyber intrusion detection using ensemble of deep learning with prediction scoring based optimized feature sets for IoT networks, Cyber Secur. Appl., 3 (2025), 100088. https://doi.org/10.1016/j.csa.2025.100088 doi: 10.1016/j.csa.2025.100088
[21]	S. Misra, A step by step guide for choosing project topics and writing research papers in ICT related disciplines, In: Misra, S., Muhammad-Bello, B. (eds) Information and Communication Technology and Applications. ICTA 2020, Communications in Computer and Information Science, Springer, Cham, 3 (2021), 727−744. https://doi.org/10.1007/978-3-030-69143-1_55
[22]	E. A. Adeniyi, R. O. Ogundokun, S. Misra, J. B. Awotunde, K. M. Abiodun, Enhanced security and privacy issue in multi-tenant environment of green computing using blockchain technology, In: Blockchain applications in the smart era, Springer, Cham, 2022, 65−83. https://doi.org/10.1007/978-3-030-89546-4_4
[23]	W. Guo, S. Liu, L. Weng, X. Liang, Power grid load forecasting using a CNN-LSTM network based on a multi-modal attention mechanism, Appl. Sci., 15 (2025), 2435. https://doi.org/10.3390/app15052435 doi: 10.3390/app15052435
[24]	H. Zhang, D. Zhu, Y. Gan, S. Xiong, End-to-end learning-based study on the Mamba-ECANet model for data security intrusion detection, J. Inform. Technol. Policy, 2024, 1−17. https://doi.org/10.62836/jitp.v1i1.219
[25]	Y. Wu, Z. Zang, X. Zou, W. Luo, N. Bai, Y. Xiang, et al., Graph attention and Kolmogorov–Arnold network based smart grids intrusion detection, Sci. Rep., 15 (2025), 8648. https://doi.org/10.1038/s41598-025-88054-9 doi: 10.1038/s41598-025-88054-9
[26]	L. Sana, M. M. Nazir, J. Yang, L. Hussain, Y. L. Chen, C. S. Ku, et al., Securing the IoT cyber environment: Enhancing intrusion anomaly detection with vision transformers, IEEE Access, 2024. https://doi.org/10.1109/ACCESS.2024.3404778
[27]	H. Mancy, Q. H. Naith, SwinIoT: A hierarchical transformer-based framework for behavioral anomaly detection in IoT-Driven smart cities, IEEE Access, 2025. https://doi.org/10.1109/ACCESS.2025.3551207
[28]	J. Huang, Z. Chen, A. Z. Liu, H. Zhang, H. X. Long, Improved intrusion detection based on hybrid deep learning models and federated learning, Sensors, 24 (2024), 4002. https://doi.org/10.3390/s24124002 doi: 10.3390/s24124002
[29]	C. Su, J. Huang, S. Dong, Y. He, J. Li, L. Hu, et al., Transformer-gate recurrent unit-based hourly purified natural gas prediction algorithm, Processes, 13 (2025), 116. https://doi.org/10.3390/pr13010116 doi: 10.3390/pr13010116
[30]	X. Ru, An improved butterfly optimization algorithm for numerical optimization and parameter identification of photovoltaic model, Eng. Let., 2025.
[31]	M. Lin, Y. Luo, S. Chen, Z. Qiu, Z. Dai, Low-voltage biological electric shock fault diagnosis based on the attention mechanism fusion parallel convolutional neural network/bidirectional long short-term memory model, Mathematics, 12 (2024), 3984. https://doi.org/10.3390/math12243984 doi: 10.3390/math12243984
[32]	U. I. Maijeddah, M. Abdullahi, I. H. Hassan, A hybrid transfer learning model with optimized SVM using honey badger optimization algorithm for multi-class lung cancer classification, Sci. World J., 19 (2024), 977−986. https://doi.org/10.4314/swj.v19i4.10 doi: 10.4314/swj.v19i4.10
[33]	https://research.unsw.edu.au/projects/bot-iot-dataset
[34]	https://research.unsw.edu.au/projects/toniot-datasets
[35]	I. Tareq, B. M. Elbagoury, S. El-Regaily, E. S. M. El-Horbaty, Analysis of ToN-IoT, UNW-NB15, and Edge-IIoT datasets using DL in cybersecurity for IoT, Appl. Sci., 12 (2022), 9572. https://doi.org/10.3390/app12199572 doi: 10.3390/app12199572
[36]	I. Katib, M. Ragab, Blockchain-assisted hybrid Harris Hawks optimization based deep DDoS attack detection in the IoT environment, Mathematics, 11 (2023), 1887. https://doi.org/10.3390/math11081887 doi: 10.3390/math11081887
[37]	M. Zeeshan, Q. Riaz, M. A. Bilal, M. K. Shahzad, H. Jabeen, S. A. Haider, et al., Protocol-based deep intrusion detection for DoS and DDoS attacks using UNSW-NB15 and Bot-IoT data-sets, IEEE Access, 10 (2021), 2269−2283. https://doi.org/10.1109/ACCESS.2021.3137201 doi: 10.1109/ACCESS.2021.3137201
[38]	C. Yang, L. Wu, J. Xu, Y. Ren, B. Tian, Z. Wei, Graph learning framework for data link anomaly detection, IEEE Access, 2024. https://doi.org/10.1109/ACCESS.2024.3445533

Reader Comments

Your name:*

Email:*
© 2025 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)