View Proposal

---

Proposer

Idris Ibrahim

Title

Lightweight Machine Learning–Based Detection of Malicious IoT Behaviour in SOHO Networks

Goal

The goal of this project is to design and evaluate a lightweight machine learning–based approach for detecting malicious IoT device behaviour in SOHO networks using network traffic data. The project focuses on feasibility, detection effectiveness, and suitability for deployment on low-cost, resource-constrained devices.

Description

This project explores the use of machine learning to detect malicious IoT device behaviour in Small Office/Home Office (SOHO) networks using network traffic analysis. The focus is on designing and evaluating a practical, resource-efficient detection approach that can operate on low-cost hardware, such as home routers or edge devices. Rather than replicating enterprise intrusion detection systems, the project aims to demonstrate the feasibility and effectiveness of lightweight machine learning techniques for improving security visibility in SOHO environments.

Resources

Background

Basic networking and machine learning, programming in any high-level language (Python recommended for ML libraries), and interest in IoT security.

Url

Difficulty Level

Moderate

Ethical Approval

InterfaceOnly

Number Of Students

1

Supervisor

Idris Ibrahim

Keywords

Degrees

Bachelor of Science in Computer Science
Master of Science in Artificial Intelligence
Master of Science in Artificial Intelligence with SMI
Master of Science in Computer Science for Cyber Security
Master of Science in Data Science
Master of Science in Network Security
Bachelor of Science in Computing Science
Bachelor of Science in Computer Science (Cyber Security)
MSc Applied Cyber Security