Securing 5G IoT Networks: A Machine Learning Framework for Zero-Trust Intrusion Detection System - Configuration Manual

Sep 17, 2026

Uploaded by Theodora

Configuration manual for an MSc Cybersecurity practicum project on machine-learning–based intrusion detection in 5G IoT networks under a Zero Trust approach. It documents the end-to-end implementation workflow including dataset handling for CICIOT2023 and Bot-IoT, cloud hardware and software environment setup using Google Colab Pro, and the required Python libraries with versions. It details data preprocessing steps such as mounting and loading, cleaning, feature scaling, SMOTE class balancing, correlation analysis, label encoding, and train-test splitting to support reproducible evaluation.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages16

Reading Time40 min

AccessFree to download

1. Introduction

2. Hardware requirements/environment used.

3. Software Requirements

4. Datasets Management

5. Libraries Imported

Data Loading, Manipulation, and Preprocessing

Data Loading, Manipulation, and Preprocessing and Machine Learning Algorithms

6. Data Preparation and Processing stage

CICIOT2023—Data Preparation and Processing Stage

BoT_IoT—Data Preparation and Processing Stage

Configuration Manual MSc Practicum 2 Master of Science in Cybersecurity Preetham Charan Sridhar Student ID: x23183683 School of Computing National College of Ireland Supervisor: Vikas Sahni National College of Ireland MSc Project Submission Sheet School of Computing PREETHAM CHARAN SRIDHAR Student Name: x23183683 Student ID: ……………………………………………………………………………………………………………..…… MSC Cyber Security 2024 Programme: ……………………………………………………………… Year: ………………………….. Module: Lecturer: Submission Due Date: MSc Practicum 2 | VIKAS SAHNI | | --- | | 12-12-2024 | Securing 5G IoT Networks: A Machine Learning Framework for ZeroProject Title: Trust Intrusion Detection System 2126 16 Word Count: Page Count: . . I hereby certify that the information contained in this (my submission) is information pertaining to research I conducted for this project. All information other than my own contribution will be fully referenced and listed in the relevant bibliography section at the rear of the project. ALL internet material must be referenced in the bibliography section. Students are required to use the Referencing Standard specified in the report template. To use other author's written or electronic work is illegal (plagiarism) and may result in disciplinary action. PREETHAM CHARAN SRIDHAR Signature: 12-12-2024 Date: PLEASE READ THE FOLLOWING INSTRUCTIONS AND CHECKLIST | Attach a completed copy of this sheet to each project (including multiple copies) | □ | | --- | --- | | Attach a Moodle submission receipt of the online project submission, to each project (including multiple copies) . | □ | | You must ensure that you retain a HARD COPY of the project, both for your own reference and in case a project is lost or mislaid. It is not sufficient to keep a copy on computer. | □ | Assignments that are submitted to the Programme Coordinator Office must be placed into the assignment box located outside the office. | Office Use Only | | | --- | --- | | Signature: | | | Date: | | Penalty Applied (if applicable): Configuration Manual Preetham Charan Sridhar Student ID: x23183683 1. Introduction This configuration manual walks through the implementations of machine learning models for intrusion detection in 5G IoT networks. It details the packages, libraries, and steps needed for data preprocessing, model training, and evaluation. In fact, this manual supports replication experiments-including those with hybrid models and Zero Trust integration-to improve IoT network security. 2. Hardware requirements/environment used. Cloud Hardware • RAM – up to 51GB • Disk Storage-225.8 GB available for temporary file storage during runtime • Compute Units-100 units for operations • GPU-NVIDIA Tesla P100 or T4 (CUDA-enabled) for accelerated training • Backend-Python 3 Google Compute Engine • Internet Connection - High-speed internet for seamless access to the Colab Pro environment and dataset uploads. 3. Software Requirements Software tools and environment used, • Cloud Platform-Google Colab Pro. • Operating System-Not required locally, runs entirely on Colab Pro backend. • Programming Language-Python 3.8+ (pre-installed in Colab Pro) . • Development Environment-Jupyter Notebook interface (via Colab Pro) . • Data Integration-Google Drive integration for seamless dataset management. 4. Datasets Management The datasets (CICIOT2023 and Bot-IoT) are utilized in the research, and these datasets were uploaded and accessed via Google Drive within Colab Pro. 5. Libraries Imported The library list is detailed and categorized into Data Loading, Manipulation, and Preprocessing and Machine Learning Algorithms. Data Loading, Manipulation, and Preprocessing Libraries and Versions • Pandas (2.2.2) • NumPy (1.26.4) • Scikit-learn (1.5.2) • XGBoost (2.1.3) • Matplotlib (3.8.0) • Seaborn (0.13.2) • Imbalanced-learn (0.12.4) 6. Data Preparation and Processing

FAQs

What is the purpose of this configuration manual?

It explains how to implement machine learning models for intrusion detection in 5G IoT networks, including the steps and required packages for preprocessing, training, and evaluation with Zero Trust integration.

Which cloud hardware and backend environment are used?

The manual lists up to 51GB RAM, 225.8GB temporary disk storage, 100 compute units, and an NVIDIA Tesla P100 or T4 GPU (CUDA-enabled), using Python 3 on Google Compute Engine with high-speed internet for Colab Pro.

Which datasets and preprocessing steps are covered?

It uses CICIOT2023 and Bot-IoT accessed through Google Drive in Colab Pro, and covers loading, cleaning, StandardScaler feature scaling, SMOTE class balancing, correlation-based feature handling, label encoding, and an 80/20 train-test split.

Sep 17, 2026

Uploaded by Theodora