Methodology for detecting and countering multi-vector threats to information security of a decentralized IoT system
Abstract
The paper proposes a methodology for detecting and countering multi-vector information security threats in decentralized IoT networks. The proposed solution integrates multidimensional reconstruction of network traffic, a hybrid architecture of convolutional neural networks (CNN) and LSTM for analyzing spatio-temporal dependencies, and a data cleaning algorithm to reduce computational costs. Testing on the CIC IoT Dataset 2023 allowed us to conduct a synthesized experiment and compare the effectiveness of the methodology with prototype methods. The results demonstrate increased accuracy (99.1%), recall (99.3%) and computational efficiency, reducing data processing costs by 20–30%. The proposed solution provides high performance under limited computing resources and is universal for detecting various types of attacks, including DDoS, Brute Force, SQL injection and XSS.
Full Text:
PDF (Russian)References
A vulnerability detection method for IoT protocol based on parallel fuzzy algorithm. Han, Yinfeng et al. Heliyon, Volume 10, Issue 12, e31846
Meysam Ghahramani, Rahim Taheri, Mohammad Shojafar, Reza Javidan, Shaohua Wan, Deep Image: A precious image based deep learning method for online malware detection in IoT environment, Internet of Things, Volume 27, 2024, 101300, ISSN 2542-6605, https://doi.org/10.1016/j.iot.2024.101300.
Lixia Xie, Bingdi Yuan, Hongyu Yang, Ze Hu, Laiwei Jiang, Liang Zhang, Xiang Cheng, MRFM: A timely detection method for DDoS attacks in IoT with multidimensional reconstruction and function mapping, Computer Standards & Interfaces, Volume 89, 2024, 103829, ISSN 0920-5489, https://doi.org/10.1016/j.csi.2023.103829.
Prabhat Kumar, Alireza Jolfaei, A.K.M Najmul Islam, An enhanced Deep-Learning empowered Threat-Hunting Framework for software-defined Internet of Things, Computers & Security, Volume 148, 2025, 104109, ISSN 0167-4048, https://doi.org/10.1016/j.cose.2024.104109.
Yilixiati Abudurexiti, Guangjie Han, Fan Zhang, Li Liu, An explainable unsupervised anomaly detection framework for Industrial Internet of Things, Computers & Security, Volume 148, 2025, 104130, ISSN 0167-4048, https://doi.org/10.1016/j.cose.2024.104130.
Alireza Zohourian, Sajjad Dadkhah, Heather Molyneaux, Euclides Carlos Pinto Neto, Ali A. Ghorbani, IoT-PRIDS: Leveraging packet representations for intrusion detection in IoT networks, Computers & Security, Volume 146, 2024, 104034, ISSN 0167-4048, https://doi.org/10.1016/j.cose.2024.104034.
Tao Yang, JiangChuan Chen, Hongli Deng, Baolin He, A lightweight intrusion detection algorithm for IoT based on data purification and a separable convolution improved CNN, Knowledge-Based Systems, Volume 304, 2024, 112473, ISSN 0950-7051, https://doi.org/10.1016/j.knosys.2024.112473.
Methods of protecting Internet of Things systems from DDoS attacks / V. I. Petrenko, N. Dibrov, S. A. Goryainov, D. A. Dikansky // Actual aspects of the development of science and society in the era of digital transformation: Collection of materials of the XIV International scientific and practical conference, Moscow, April 29, 2024. - Moscow: Center for the Development of Education and Science, 2024. - Pp. 190-197. - EDN EKDRPY.
Analysis of current threats to integrity for industrial Internet of Things systems / F. B. Tebueva, S. M. Petrosyan, D. A. Dikansky [et al.] // Development of science and practice in a globally changing world under risks (code -MKRNP): Collection of materials of the XXVII International scientific and practical conference, Moscow, April 25, 2024. – Moscow: OOO "Izdatelstvo "Ekonomicheskoe obrazovanie", 2024. – P. 196-202. – EDN FLLOAF.
Iskhakova, A. O. Protection of cyber-physical system control interfaces from multi-vector application-level attacks aimed at disrupting availability / A. O. Iskhakova // Management of Large-Scale Systems Development (MLSD'2023): Proceedings of the Sixteenth International Conference, Moscow, September 26-28, 2023. – Moscow: V.A. Trapeznikov Institute of Control Sciences of the Russian Academy of Sciences, 2023. – P. 1301-1307. – DOI 10.25728/mlsd.2023.1301. – EDN URVDQM.
Slesarchik, K. F. Artificial neural network in the problem of detecting a multi-vector DDOS attack / K. F. Slesarchik // Actual problems of infotelecommunications in science and education (APINO 2020): Collection of scientific articles of the IX International scientific-technical and scientific-methodical conference. In 4 volumes, St. Petersburg, February 26-27, 2020. Volume 2. - St. Petersburg: St. Petersburg State University of Telecommunications named after prof. M.A. Bonch-Bruevich, 2020. - P. 565-570. - EDN VQKWDL.
Ogur, M. G. Mathematical model for the implementation of multi-vector attacks on IoT systems based on the analysis of network traffic flow / M. G. Ogur // Caspian Journal: Management and High Technologies. - 2024. - No. 2 (66). - P. 81-92. - EDN EUYRPT.
Refbacks
- There are currently no refbacks.
Abava Кибербезопасность IT Congress 2024
ISSN: 2307-8162