Core Module Information
Module title: Artificial Intelligence for Cybersecurity

SCQF level: 11:
SCQF credit value: 20.00
ECTS credit value: 10

Module code: CSN11132
Module leader: Jawad Ahmad
School School of Computing, Engineering and the Built Environment
Subject area group: Cyber Security and Systems Engineering

There are no pre-requisites for this module to be added

Description of module content:

The aim of this course is to develop theoretical understanding and knowledge as well as hands-on experience of applying artificial intelligence (AI) and machine learning-based tools for cybersecurity and network security. The series of theoretical lectures of module covers basic background knowledge of statistics and probability for artificial intelligence. Students will start with learning basic data analytics concepts including data visualization, data pre-processing, missing values and outlier detection, dealing with missing values and outliers in data. The common machine learning algorithms used for pattern recognition will be discussed from theoretical perspective. The module will be further directed to applying machine learning algorithms for cybersecurity. The labs will start the journey from basic Python/MATLAB programming toward applying and developing machine learning algorithms for pattern recognition in data. Publicly available dataset will be used to train and assess the performance of these algorithms.
The main areas covered in this module are:
• Big Data, Data Visualization and Pre-processing, Missing Values and Outlier detection
• Machine Learning and Deep Learning, Supervised, Semi-supervised and Unsupervised Learning Techniques,
• Regression, Classification, Clustering,
o K-Nearest Neighbour (KNN), Decision Tree (DT), Bayesian Algorithm, Support Vector Machine, Neural Networks and Convolutional Neural Network (CNN)
• Training and Testing Machine Learning Algorithms, Machine Learning Evaluating Parameters, Student’s T-test, Accuracy, Precision, Recall, F1-Score, and Confusion Matrix, Receiver Operating curve (ROC), Training, Validation and Testing.
• Generalisation, Overfitting and Underfitting Problems, Cross Validation, Regularisation, Dropout
• Network Anomaly Detection with AI, Intrusion Detection with AI, Splunk, Spam or Ham Classifier with AI, Detecting Spam email cybersecurity threats using AI
• Fraud Prevention with Cloud AI, Introduction to Federated Learning
• Integration of Blockchain and Machine Learning

Learning Outcomes for module:

LO1: Demonstrate extensive knowledge about machine learning algorithms for cybersecurity.
LO2: A critical understanding of decentralized learning frameworks for cybersecurity.
LO3: Detailed and critical awareness about potential application areas of machine learning in cybersecurity.

Full Details of Teaching and Assessment
2023/4, Trimester 1, FACE-TO-FACE,
Occurrence: 001
Primary mode of delivery: FACE-TO-FACE
Location of delivery: MERCHISTON
Member of staff responsible for delivering module: Jawad Ahmad
Module Organiser:

Student Activity (Notional Equivalent Study Hours (NESH))
Mode of activityLearning & Teaching ActivityNESH (Study Hours)
Face To Face Lecture 24
Face To Face Practical classes and workshops 24
Independent Learning Guided independent study 152
Total Study Hours200
Expected Total Study Hours for Module200

Type of Assessment Weighting % LOs covered Week due Length in Hours/Words
Class Test 50 1 10 HOURS= 02.00, WORDS= 0
Project - Practical 50 2, 3 14/15 HOURS= 40.00, WORDS= 0
Component 1 subtotal: 100
Component 2 subtotal: 0
Module subtotal: 100

Indicative References and Reading List - URL:
Contact your module leader