Article: Harnessing machine learning for dynamic defence in the battle against 5G cybersecurity threats Journal: International Journal of Communication Networks and Distributed Systems (IJCNDS) 2025 Vol.31 No.3 pp.318 - 345 Abstract: The evolution mobile network highlighted by means of 5G networks, has caused advanced cyber threats necessitating modern security features. The adaptive multi-layer threat defence machine addresses these threats with machine getting to know (ML), presenting robust resilience. It surpasses traditional strategies via deploying ML algorithms throughout more than one network layers. Network behaviour profiling (NBP) establishes baselines for customers/gadgets, detecting deviations as early malicious signs. Intent prediction (IP) visually anticipates person purpose, while anomaly detection (AD) identifies subtle anomalies. The system's centre, decentralised associative learning (federated learning), keeps confidentiality and model integrity. Continuous Threat Intelligence Integration (TII) permits proactive responses to rising threats. This integrated approach provides better protection for 5G networks, creating an adaptive defence via profiling, prediction and anomaly detection. The adaptive multi-layer threat defence system, combining flexibility, privacy, and scalability, ushers in a generation in which ML supports technological development. Inderscience Publishers - linking academia, business and industry through research

Title: Harnessing machine learning for dynamic defence in the battle against 5G cybersecurity threats

Authors: V. Aanandaram; P. Deepalakshmi

Addresses: Department of Computer Applications, Kalasalingam Academy of Research and Education, Krishnankovil, 626126, Tamilnadu, India ' Department of Computer Science and Engineering, Kalasalingam Academy of Research and Education, Krishnankovil, 626126, Tamilnadu, India

Abstract: The evolution mobile network highlighted by means of 5G networks, has caused advanced cyber threats necessitating modern security features. The adaptive multi-layer threat defence machine addresses these threats with machine getting to know (ML), presenting robust resilience. It surpasses traditional strategies via deploying ML algorithms throughout more than one network layers. Network behaviour profiling (NBP) establishes baselines for customers/gadgets, detecting deviations as early malicious signs. Intent prediction (IP) visually anticipates person purpose, while anomaly detection (AD) identifies subtle anomalies. The system's centre, decentralised associative learning (federated learning), keeps confidentiality and model integrity. Continuous Threat Intelligence Integration (TII) permits proactive responses to rising threats. This integrated approach provides better protection for 5G networks, creating an adaptive defence via profiling, prediction and anomaly detection. The adaptive multi-layer threat defence system, combining flexibility, privacy, and scalability, ushers in a generation in which ML supports technological development.

Keywords: AML-TDS; adaptive multi-layered threat defence system; threat intelligence; anomaly detection; privacy preservation; 5G network security; NBP; network behaviour profiling; cyber threats.

DOI: 10.1504/IJCNDS.2025.145919

International Journal of Communication Networks and Distributed Systems, 2025 Vol.31 No.3, pp.318 - 345

Received: 22 Mar 2024
Accepted: 26 May 2024
Published online: 30 Apr 2025 *

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

Title: Harnessing machine learning for dynamic defence in the battle against 5G cybersecurity threats

Keep up-to-date