Title: A novel method to increase the security in 5G networks using deep learning

Authors: A. Rajasekar; R. Ramamoorthi; M. Ramya; Vinod Arunachalam

Addresses: Department of Artificial Intelligence and Data Science, Sri Sairam Institute of Technology, Sai Leo Nagar, West Tambaram, Chennai, 44, India ' Department of EEE, Government College of Engineering – Dharmapuri, Dharmapuri, India ' Department of ECE, S.A. Engineering College, Chennai-77, India ' Department of ECE, Government College of Engineering Dharmapuri, Dharmapuri-636704, India

Abstract: Wireless networks are being forced to handle a greater amount of data due to a variety of circumstances, and this trend is progressing at a rapid rate. The denial of service (DoS) attacks have the highest rate of growth target the expanding computational network infrastructures all over the globe. As a consequence of this, the objective of this study is to come up with an innovative model for the identification of DoS attacks on 5 G networks. The model will go through two phases: the first will be feature extraction, and the second will be attack detection. In order to successfully carry out the detection, classifiers that have long short-term memories (LSTM) are utilised. The whale optimisation algorithm (WOA) model works to optimise the weight of the LSTM. The detected output of a hybrid model that has been trained appropriately provides the accuracy rate of 96.5%

Keywords: 5G; deep learning; dos attacks; denial-of-service; whale optimisation algorithm; WOA.

DOI: 10.1504/IJESDF.2025.145879

International Journal of Electronic Security and Digital Forensics, 2025 Vol.17 No.3, pp.419 - 431

Received: 04 Aug 2023
Accepted: 21 Sep 2023
Published online: 30 Apr 2025 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article