Simulation of IIoT-Driven Attack Vectors on 5G Core Networks - Dataset Generation and Machine Learning Based Detection

Aug 5, 2026

Upload by Eden

5G adoption accelerates Industrial Internet of Things (IIoT) innovation, but the combination expands security vulnerabilities in 5G core networks. The large number of connected devices and insufficient protection in IIoT endpoints create opportunities for intruders. This work simulates multiple IIoT-originated attack types, aggregates the resulting observations into a structured dataset, and trains a machine learning model for threat detection. The dataset supports evaluation of alternative intrusion detection models and advances resilient defenses for 5G infrastructures under emerging cyber threats.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages4

Reading Time10 min

AccessFree to download

Introduction

Security risks from IIoT to 5G core networks

ML-based approaches for 5G threat detection

Proposed approach: attack simulation, dataset, and ML detection

Simulation of IIoT-Driven Attack Vectors on 5G Core Networks: Dataset Generation and Machine Learning Based Detection Suranga Prasad Centre for Wireless Communications University of Oulu Oulu, Finland Pramod Munaweera Centre for Wireless Communications University of Oulu Oulu, Finland Tharaka Hewa Centre for Wireless Communications University of Oulu Oulu, Finland Suranga.WengappuliArachchige@oulu.fi pramod.munaweerakankanamge@oulu.fi [tharaka.hewa@oulu.fi](tharaka.hewa@oulu.fi) Yushan Siriwardhana Centre for Wireless Communications University of Oulu Oulu, Finland [yushan.siriwardhana@oulu.fi](yushan.siriwardhana@oulu.fi) Mika Ylinattila Centre for Wireless Communications University of Oulu Oulu, Finland [mika.ylinattila@oulu.fi](mika.ylinattila@oulu.fi) Abstract The emergence of 5G technology has accelerated the development of Industrial Internet of Things (IIoT) applications, enabling a wide range of innovations across multiple industries. However, the integration of 5G and IIoT introduces new security vulnerabilities in core networks due to the vast number of connected devices and the lack of robust security measures in these devices. These vulnerabilities provide intruders with new opportunities to attack the core network. In our research, we demonstrate several types of potential attacks from IoT devices on the core network, collect the attack data into a proper dataset, and implement a Machine Learning (ML) model to detect these threats. The collected data can be used to test different ML models designed to detect intrusions in the core network. The results of this work will contribute to the development of advanced security measures, enhancing the resilience and reliability of 5G infrastructures against emerging cyber threats. Keywords 5G Core, Security, IIoT, Attack, Dataset, Machine Learning ACM Reference Format: Suranga Prasad, Pramod Munaweera, Tharaka Hewa, Yushan Siriwardhana, and Mika Ylinattila. 2024. Simulation of IIoT-Driven Attack Vectors on 5G Core Networks: Dataset Generation and Machine Learning Based Detection. In 14th International Conference on the Internet of Things (IoT 2024), November 19–22, 2024, Oulu, Finland. ACM, New York, NY, USA, 4 pages. [https://doi](https://doi). org/10.1145/3703790.3703815 1 Introduction 5G technology offers faster speeds, lower latency, and greater capacity than previous versions [6] . This enhanced connectivity is crucial for the IIoT, which relies on 5G to connect and manage industrial devices, enabling smarter factories and real-time data This work is licensed under a Creative Commons Attribution International 4.0 License. IoT 2024, Oulu, Finland © 2024 Copyright held by the owner/author(s) . ACM ISBN 979-8-4007-1285-2/24/11 [https://doi.org/10.1145/3703790.3703815](https://doi.org/10.1145/3703790.3703815) analysis. With 5G’s robust communication capabilities, IIoT applications are transforming industrial processes across various sectors [17][18] . However, IIoT devices are vulnerable to attacks due to factors like weak security measures, such as default passwords and inadequate encryption. Many IIoT devices lack advanced security features and suffer from poor management, including infrequent updates or reliance on outdated hardware. The scale and diversity of IIoT devices create a large attack surface, worsened by less secure communication protocols and limited device resources that can’t support complex security software. Additionally, physical vulnerabilities, weak authentication, and supply chain issues increase the risk of breaches in IIoT systems [7][11] . Real-world attacks like Stuxnet [4], the Ukraine power grid hack [3], the Mirai Botnet [1], and Triton malware [5] reveal significant vulnerabilities in IIoT systems, particularly in critical infrastructure. An attack on the 5G core network can severely impact various industries due to its central role in managing essential network functions [6] . For instan

FAQs

Why do IIoT deployments create new security vulnerabilities for 5G core networks?

IIoT increases the number and diversity of connected devices while many endpoints lack robust protections such as strong authentication, proper encryption, and timely updates. Weak protocols and limited device resources further enlarge the attack surface.

What is the document’s main contribution to 5G core security research?

It simulates multiple IIoT-driven attack types targeting the 5G core, collects the generated attack data into a dataset, and uses machine learning to detect intrusions and anomalies.

How can the generated dataset be used by other researchers?

The dataset can be used to test and compare different machine learning models for intrusion detection in the 5G core network, enabling research on additional attack types and improved detection performance.

Aug 5, 2026

Upload by Eden