WM9PH-15 Artificial Intelligence for Cyber Security

Department: WMG
Level: Taught Postgraduate Level
Module leader: Christo Panchev
Credit value: 15
Assessment: 100% coursework
Study location: University of Warwick main campus, Coventry

Introductory description

AI-based solutions are having a significant impact in a number of areas, including cyber security. This module will provide students with an in-depth understanding of the main machine learning models, and their practical application in both offensive and defensive cyber operations.
Furthermore, with the increasing ubiquity of AI in society and industry, the security of AI itself is becoming a critical factor. The module aims to cover this issue as part of the development and deployment of AI-based solutions.

Module aims

The module aim to develop student's knowledge of the development and application of the most common machine learning models, and in particular a critical understanding of the applicability of each machine learning algorithms in the solution of a particular problem (class of problems). It will cover the best practice and main steps of developing AI-based solution, including data collection/engineering and pre-processing, model design, training and evaluation, and deployment.

Outline syllabus

This is an indicative module outline only to give an indication of the sort of topics that may be covered. Actual sessions held may differ.

Some of the main topics covered in the module include:
Methodology of developing an AI-based solution
Data collection, engineering and pre-processing
Unsupervised learning (clustering) models, such as k-means, nearest neighbour
Supervised learning models, such as linera/logistic regression, decision trees, random forest, SVM
Neural Networks (Deep learning) models, such as NLP, CNN, LSTM
Auto encoders
Generative AI
Security of AI

Learning outcomes

By the end of the module, students should be able to:

Critically analyse an application domain and applicability of machine learning models in solving a specific problem.
Collect, engineer and pre-process real-world data suitable for building machine learning models
Develop, secure and optimise the performance a machine learning model
Evaluate and interpret the results of a machine learning model.

Indicative reading list

Pattern Recognition and Machine Learning, Bishop, Christopher. Springer, 2006
Deep learning, Ian Goodfellow, Yoshua Bengio, Aaron Courville 2016
Deep Learning with Python, François Chollet, Hanning, 2022

Subject specific skills

Data analysis
Decision support automation
Application of AI in offensive and defensive cyber operations
Security of AI

Transferable skills

Critical thinking
Analytical thinking

Study time

Type	Required
Supervised practical classes	30 sessions of 1 hour (100%)
Total	30 hours

Private study description

Further research and experimental work.

Costs

No further costs have been identified for this module.

You must pass all assessment components to pass the module.

Assessment group A

	Weighting	Study time	Eligible for self-certification
Assessment component
Machine learning project	100%	60 hours	Yes (extension)
Students will be provided with a data set and set a particular problem to solve. They will be expected to decide and justify a choice of a machine learning model, develop and evaluate a solution.
Reassessment component is the same

Feedback on assessment

In a feedback form

There is currently no information about the courses for which this module is core or optional.