OPTIMIZATION OF NEURAL NETWORK COMPUTATION USING INTEGER ARITHMETIC
DOI:
https://doi.org/10.26906/SUNZ.2025.2.125Keywords:
neural network, intrusion detection, network traffic, datasets, analysisAbstract
The rapid growth in the popularity of Internet of Things (IoT) systems makes the issue of improving security increasingly important. However, since most sensors and actuators are based on energy-efficient microcontrollers, the use of popular neural network-based intrusion detection models is practically infeasible for such devices. The aim of this work is to analyze existing intrusion detection systems based on network information in terms of their applicability to energy-efficient microcontrollers with limited computational capabilities. The following results were obtained: the vast majority of studies propose large-scale neural network models that cannot be used on small microcontrollers. Most research focuses solely on detection accuracy, without considering performance or resource consumption. However, several studies propose reducing the number of network protocol parameters used for detection, and analyze the impact of this reduction on detection effectiveness. The most popular publicly available datasets suitable for evaluating and comparing intrusion detection efficiency were also identified. Conclusions: neural network models that use a reduced set of network parameters for recognition, combined with neural network computation optimization, represent a promising direction for future research. Publicly available datasets enable comparison with existing solutions.Downloads
References
1. Khanna, A., Kaur, S. (2020), “Internet of Things (IoT), Applications and Challenges: A Comprehensive Review”, Wireless Pers Commun 114, 1687–1762, doi: https://doi.org/10.1007/s11277-020-07446-4
2. Kumar, S., Tiwari, P. & Zymbler, M. (2019), “Internet of Things is a revolutionary approach for future technology enhancement: a review”, J Big Data 6, 111, doi: https://doi.org/10.1186/s40537-019-0268-2
3. Choudhary, A. (2024), “Internet of Things: a comprehensive overview, architectures, applications, simulation tools, challenges and future directions”, Discov Internet Things 4, 31, doi: https://doi.org/10.1007/s43926-024-00084-3
4. (2023), “IoT Security: 15 Types of Attacks with Real-World Examples”, Inovasense, url: https://www.inovasense.com/15-types-of-attacks-with-real-world-examples/
5. Chakraborty, S., Pandey, S.K., Maity, S. (2024), “Detection and Classification of Novel Attacks and Anomaly in IoT Network using Rule based Deep Learning Model”, SN COMPUT. SCI. 5, 1056, doi: https://doi.org/10.1007/s42979-024-03429-5
6. Bensaoud, A., Kalita, J. (2025), “Optimized detection of cyber-attacks on IoT networks via hybrid deep learning models”, Ad Hoc Networks 170: 103770, doi: https://doi.org/10.48550/arXiv.2502.11470
7. Almohaimeed, M.; Albalwy, F. (2024), “Enhancing IoT Network Security Using Feature Selection for Intrusion Detection Systems”, Appl. Sci., 14, 11966, doi: https://doi.org/10.3390/app142411966
8. Newman, R.C. (2009), “Computer Security: Protecting Digital Resources”, Jones & Bartlett Learning, url: https://www.jblearning.com/catalog/productdetails/9780763759940?srsltid=AfmBOop8BLj-VJGp7IKaVkbLmnhpqhMjpdoF-8hPzKwlAPyfAaoVcuUQ
9. Thottan M., Chuanyi Ji. (2003), "Anomaly detection in IP networks", IEEE Transactions on Signal Processing, vol. 51, no. 8, pp. 2191-2204, doi: https://doi.org/10.1109/TSP.2003.814797
10. Dong, H., Kotenko, I. (2025), “Cybersecurity in the AI era: analyzing the impact of machine learning on intrusion detection”, Knowl Inf Syst, doi: https://doi.org/10.1007/s10115-025-02366-w
11. Ajagbe, S.A., Awotunde, J.B. & Florez, H. (2024), “Intrusion Detection: A Comparison Study of Machine Learning Models Using Unbalanced Dataset”, SN COMPUT. SCI. 5, 1028, doi: https://doi.org/10.1007/s42979-024-03369-0
12. Hussein Ali, A., Charfeddine, M., Ammar, B. et al. (2024), “Unveiling machine learning strategies and considerations in intrusion detection systems: a comprehensive survey”, Frontiers in Computer Science, doi:https://doi.org/10.3389/fcomp.2024.1387354
13. Ring, M., Wunderlich, S., Grüdl, D. et al. (2017), “Flow-based benchmark data sets for intrusion detection”, ECCWS 2017 16th European Conference on Cyber Warfare and Security. Academic Conferences and publishing limited, url:https://books.google.com.ua/books?hl=uk&lr=&id=uFA8DwAAQBAJ&oi=fnd&pg=PA361&dq=intrusion+detection+based+on+network+data&ots=YUq_mFVm5C&sig=J12NbOfJq4fMxm7JXE-JWvFkmgM&redir_esc=y#v=onepage&q=intrusion%20detection%20based%20on%20network%20data&f=false
14. Mohammadpour, L., Ling, T. C., Liew, C. S., & Aryanfar, A. (2022), “A Survey of CNN-Based Network Intrusion Detection”, Applied Sciences, 12(16), 8162, doi: https://doi.org/10.3390/app12168162
15. Zhen Yang, Xiaodong Liu, Tong Li, Di Wu, Jinjiang Wang, Yunwei Zhao, Han Han. (2022), “A systematic literature review of methods and datasets for anomaly-based network intrusion detection”, Computers & Security, Volume 116, doi:https://doi.org/10.1016/j.cose.2022.102675
16. Chou D., Jiang, M. (2021), “A Survey on Data-driven Network Intrusion Detection”, ACM Computing Surveys (CSUR), Volume 54, Issue 9, doi: https://doi.org/10.1145/3472753
17. Abdi, M., Razzak, M. I., & Zaib, A. (2020), "Neural Networks for Network Intrusion Detection Systems: A Survey", Computers, Materials & Continua, 63(3), 1401-1420, doi: https://doi.org/10.32604/cmc.2020.011216
18. Zhang, Y., Wang, S., & Jin, X. (2019), "Deep Learning for Network Intrusion Detection Systems: A Survey." Future Generation Computer Systems, 101, 755-763, doi: https://doi.org/10.1016/j.future.2019.07.046
19. Siddiqui, M. K., Khan, M. A., & Zhang, L. (2020), "Challenges in the Real-Time Application of Neural Network-Based Intrusion Detection Systems.", International Journal of Computer Science and Network Security, 20(9), 56-63, doi:https://doi.org/10.22937/IJCSNS.2020.20.9.56
20. L. Nie, Z. Ning, X. Wang, X. Hu, J. Cheng and Y. Li (2020), "Data-Driven Intrusion Detection for Intelligent Internet of Vehicles: A Deep Convolutional Neural Network-Based Method", IEEE Transactions on Network Science and Engineering, vol. 7, no. 4, pp. 2219-2230, 1 Oct.-Dec. 2020, doi: https://doi.org/10.1109/TNSE.2020.2990984
21. Muneer, S., Farooq, U., Athar, A., Ahsan Raza, M., Ghazal, T.M., & Sakib, S. (2024), “A Critical Review of Artificial Intelligence Based Approaches in Intrusion Detection: A Comprehensive Analysis”, Journal of Engineering, doi:https://doi.org/10.1155/2024/3909173
22. Jia, Y., Wang, M. and Wang, Y. (2019), “Network intrusion detection algorithm based on deep neural network”, IET Inf. Secur., 2019, Vol. 13 Iss. 1, pp. 48-53, doi: https://doi.org/10.1049/iet-ifs.2018.5258
23. Zhang Y., Chen X., Jin L., Wang X., Guo D. (2019), "Network Intrusion Detection: Based on Deep Hierarchical Network and Original Flow Data", IEEE Access, vol. 7, pp. 37004-37016, doi: https://doi.org/10.1109/ACCESS.2019.2905041
24. Yang H., Wang F. (2019), "Wireless Network Intrusion Detection Based on Improved Convolutional Neural Network", IEEE Access, vol. 7, pp. 64366-64374, 2019, doi: https://doi.org/10.1109/ACCESS.2019.2917299
25. Al-Turaiki, I., Altwaijry, N. (2021), “A Convolutional Neural Network for Improved Anomaly-Based Network Intrusion Detection”, Big Data, 2021, Vol. 9, No. 3, pp. 233-252. doi: https://doi.org/10.1089/big.2020.0263
26. Mohammadpour, L., Ling, T.C., Liew, C.S., Aryanfar, A. A (2022), “Survey of CNN-Based Network Intrusion Detection”, Appl. Sci. 2022, 12, 8162, doi: https://doi.org/10.3390/app12168162
27. Komisarek, M., Pawlicki, M., Kozik, R., Hołubowicz, W., & Choraś, M. (2021), “How to Effectively Collect and Process Network Data for Intrusion Detection?”, Entropy, 23(11), 1532, doi: https://doi.org/10.3390/e23111532
28. Заковоротний, О.Ю., Хулап, А.В. (2024), “Оптимізація обчислення нейромереж за допомогою використання цілочисельної арифметики”, Системи управління, навігації та зв’язку, Том 2 № 76, doi:https://doi.org/10.26906/SUNZ.2024.2.090
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Oleksandr Zakovorotnyi, Andrii Khulap
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
