DDoS attack detection using unsupervised federated learning for 5G networks and beyond

Abstract

The rapid expansion of 5G networks, coupled with the emergence of 6G technology, has highlighted the critical need for robust security measures to protect communication infrastructures. A primary security concern in 5G core networks is Distributed Denial of Service (DDoS) attacks, which target the GTP protocol. Conventional methods for detecting these attacks exhibit weaknesses and may struggle to effectively identify novel and undiscovered attacks. In this paper, we proposed a federated learning-based approach to detect DDoS attacks on the GTP protocol within a 5G core network. The suggested model leverages the collective intelligence of multiple devices to efficiently and privately identify DDoS attacks. Additionally, we have developed a 5G testbed architecture that simulates a sophisticated public network, making it ideal for evaluating AI-based security applications and testing the implementation and deployment of the proposed model. The results of our experiments demonstrate that the proposed unsupervised federated learning model effectively detects DDoS attacks on the 5G network while preserving the privacy of individual network data. This underscores the potential of federated learning in enhancing the security of 5G networks and beyond.