Securing mobile networks:Identifying hijacking in opportunistic scenarios

Computer engineering

In an era of pervasive mobile connectivity, securing mobile network infrastructures against sophisticated cyber-attacks has become a priority. One of the critical threats is route hijacking, a deceptive practice where network traffic is maliciously rerouted through unauthorized paths, leading to data theft, interception, or service disruption. This project proposes an analytical and machine learning-based framework to detect route hijacking attacks in mobile networks using behavioral analysis of network traffic. The system leverages a real-world dataset comprising network parameters such as source and destination addresses, ports, packet count, byte volumes, states, and durations, enriched with labeled statuses like "malware attack," "route hijacking attack," and "no attack." the system learns from these attributes to accurately classify and detect abnormal routing behavior. Compared to existing systems that rely on static rule-based mechanisms, the proposed model significantly enhances detection precision and reduces false positives. By identifying early-stage hijacking patterns, this intelligent system supports proactive mobile network defense strategies, offering a scalable solution for real-time threat monitoring and mitigation.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.