The module indicative content will be centred are the following topics:



Key topics in machine learning and their relevance to cyber security

Machine Learning concepts I – Supervised Learning

Machine Learning concepts II – Unsupervised Learning

Machine Learning concepts III – Deep Learning and ML Algorithms e.g. CNN, RF, DT, KNN, SVM

Application of ML to network attack detection / prevention

Application of ML to host attack detection / prevention

Related mathematics to ML

ML-based detection of social engineering attacks

Wider implications in relation to legal, social, ethical and professional issues

Application of ML to IoT Security

Approaches to standards, principles, and used techniques

Deep level research and comparison of literature articles and sources- (including peer review processes)

Botnet Detection using ML

ML-based malware detection and analysis

ML tools for Cyber Security

ML-based Cyber Forensics

Issues facing ML in Cyber Security

Written Report – An individual coursework that evaluates the students' comprehension critically of the taught concepts. The report will be based on a practical case study for which the student must design a solution (Learning Outcomes 1 to 4).

The material will be presented through a combination of lectures, tutorials, practical exercises and directed self-study. The lectures given will be covering the theoretical content of the module giving the students a detailed understanding of various penetration testing techniques. The tutorial sessions will be provided to allow for discussion and practical exercises to be carried out. The tutorial sessions will be used to allow the student to experiment within a penetration testing environment.

1)Understand and explain the main features and definitions of key Machine Learning concepts e.g. supervised learning, and unsupervised learning.

Knowledge and Understanding
Learning


2)Demonstrate understanding of the differences between key Machine Learning concepts, use cases and functions.

Knowledge and Understanding
Analysis


3)Understand how Machine Learning technologies are being applied to Cyber security concepts, tasks, approaches and challenges.

Learning,
Analysis


4)Explain the challenges that are facing the integration of machine learning into Cyber Security and how these challenges are being addressed by the industry.

Analysis,
Problem Solving

IP Specialist, (2021), Google Certified Professional Cloud Network Engineer: Study Guide With Practice Questions & Labs - First Edition, Independently published

Gai, S. (2021), Building a Future-Proof Cloud Infrastructure: A Unified Architecture for Network, Security, and Storage Services, Addison-Wesley Professional; 1st edition

GM IT Academy, (2021), Fundamentals of Cyber Security and Network Security Master Guide and Interview Q&A¿Kindle Edition

Brumfield, C. (2022), Cybersecurity Risk Management: Mastering the Fundamentals Using the NIST Cybersecurity Framework, Wiley; 1st edition¿

Alpaydin, E. (2020), Introduction to machine learning. MIT press

Zhou, Z. (2021), Machine learning. Springer Nature

Ganapathi, P. and Shanmugapriya, D. (2020), Handbook of Research on Machine and Deep Learning Applications for Cyber Security. IGI Global

Gupta, B and Sheng, M. (2019) Machine Learning for Computer and Cyber Security. CRC Press

Chen, X., Huang, X., and Zhang, J. (2019), Machine Learning for Cyber Security. Springer

VMWare Workstation v16 or later

Kali Linux

ParrotOS

Host Machine with at least 8GB RAM, i5 or later processor, 250GB SSD Storage

On this module you will learn about some of the main methods for data analysis and machine learning in the field related to Cyber Security. Different algorithms will be explored, and students will learn how to use them to analyse data, forecast the future, and assess performance. The module will look at how these types of concepts and technologies are applied to the cyber security industry, and how they are being used to detect malicious agents and actors across both hosts and networks.