Enhancing IoT Security in 5G Networks: Mitigating DDoS Attacks With Deep Learning

Abstract

The development and implementation of Internet of Things (IoT) devices have accelerated dramatically in recent years. As a result, a robust network infrastructure is required to handle the massive volumes of data collected and transmitted to these devices. Fifth-generation (5G) is a new, comprehensive wireless system with the potential to be the primary enabling technology for the IoT. However, the rapid spread of IoT devices presents significant security challenges. Consequently, new and serious security and privacy risks have emerged. Attackers often exploit IoT devices to launch large-scale attacks, such as the Distributed Denial of Service (DDoS) attack. Recent research shows that deep learning methods are effective in identifying and preventing DDoS attacks. In this paper, we applied four deep learning algorithms: Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), Feedforward Neural Network (FNN), and Deep Neural Network (DNN). We compared the results of these algorithms with three machine learning methods: Support Vector Machine (SVM), K-Nearest Neighbor (KNN), and Stochastic Gradient Descent (SGD). These methods were used to detect DDoS attacks in a dataset specifically designed for IoT devices within 5G networks. We constructed the 5G network infrastructure using OMNeT++ with the INET and Simu5G frameworks. The dataset encompasses both normal network traffic and DDoS attacks. CNN, FNN, SVM, SGD, and KNN achieved high accuracy, with results reaching up to 99%. In contrast, LSTM and DNN showed significantly lower accuracy. These results demonstrate that deep and machine learning can improve the protection of IoT devices in 5G networks.