Knowledge Graph-Driven Security Monitoring for SS7 Signaling Traffic
Abstract
Anomaly detection in the Signaling System 7 (SS7) protocol is a critical area of focus in telecommunications, where it is essential for facilitating communication between network elements, enabling functions such as call routing, SMS delivery, and user location updates. Given the complexity of this protocol and its numerous layers and parameters, coupled with the lack of attention to security threat considerations during its design, this protocol is highly vulnerable, and detecting these vulnerabilities using traditional methods is very difficult. This paper proposes a method based on Knowledge Graph (KG) and the use of artificial intelligence techniques to detect attacks and anomalies in SS7 traffic. In this method, the KG is completed based on incoming packets, and then anomalies are searched for using predefined queries. Additionally, using a Graph Neural Network (GNN), rare subgraphs that can help detect unknown attacks are identified. Evaluation results show that this model is highly efficient in attack detection and remains implementable.
Downloads
Publication Timeline
Issue
Section
License
Copyright (c) 2025 Esmaeel Tahanian; Yasamin Teymouri, Mohsen Rezvani (Author)

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