Threat Analysis of Cyber Security in Wireless Adhoc Networks Using Hybrid Neural Network Model
- Authors: Demidov R.A.1, Zegzhda P.D.1, Kalinin M.O.1
-
Affiliations:
- Peter the Great St.Petersburg Polytechnic University
- Issue: Vol 52, No 8 (2018)
- Pages: 971-976
- Section: Article
- URL: https://journals.rcsi.science/0146-4116/article/view/175687
- DOI: https://doi.org/10.3103/S0146411618080084
- ID: 175687
Cite item
Abstract
The article discusses the problem of analysis of cybersecurity threats in wireless ad hoc networks—VANET, FANET, MARINET, MANET, WSN. The problem of neural network approximation of the function of cyber threat existence in the system is formulated. The parameters of the neural network model were optimized according to the likelihood maximization criterion on the training data set. A hybrid neural network based on recurrent and graph convolutional neural networks is proposed as a solution architecture.
About the authors
R. A. Demidov
Peter the Great St.Petersburg Polytechnic University
Author for correspondence.
Email: rd@ibks.spbstu.ru
Russian Federation, St. Petersburg, 195251
P. D. Zegzhda
Peter the Great St.Petersburg Polytechnic University
Author for correspondence.
Email: zeg@ibks.ftk.spbstu.ru
Russian Federation, St. Petersburg, 195251
M. O. Kalinin
Peter the Great St.Petersburg Polytechnic University
Author for correspondence.
Email: max@ibks.spbstu.ru
Russian Federation, St. Petersburg, 195251