University of Leeds Featured PhD Programmes
University of Liverpool Featured PhD Programmes
John Innes Centre Featured PhD Programmes
Engineering and Physical Sciences Research Council Featured PhD Programmes
Bournemouth University Featured PhD Programmes

Multi-Stage Cyber-Attack Detection: AI Approaches, Computer Science – PhD (Funded)


About This PhD Project

Project Description

The University of Exeter’s College of Engineering, Mathematics, and Physical Sciences, in partnership with British Telecom and the Engineering and Physical Sciences Research Council (EPSRC), is inviting applications for a fully-funded PhD studentship to commence in September 2019 or as soon as possible thereafter. For eligible students the studentship will cover UK/EU tuition fees plus an annual tax-free stipend of at least £15,009 for 3.5 years full-time, or pro rata for part-time study.

This PhD scholarship project will develop high-performance AI and machine learning methods to detect multistage cyber attacks. It will be jointly funded by the EPSRC DTP and BT. Modern cyber intrusion and attacks are very often delivered and achieved in multi-stages, i.e. the so-called multi-stage cyber-attacks. Famous examples include the 2017 NHS cyber attack, and the same families of malware attacked over 200,000 computers all over the world. The increase of these attacks becomes significant threats to the future cyberspace and digital world.

Multiple stages of the malware typically involve early stages and late stages which have different purposes. In the early stages, a group of malwares are used to compromise the targeted computing system so that it can be directly monitored or controlled by the hackers. The second stage malwares can cause real harms to the compromised systems or users in many different ways including, ransomwares, key loggers, banking credential stealers, anti-malware evasion components, and spreading components.

Traditional methods for detecting multistage attacks through manually reverse engineering of malware samples could not meet the demanding time and scale requirements in current and future cyberspace where attacks are organised through many distributed and networked computers and sensors. AI and machine learning methods, particularly deep learning, have proven effectiveness in automatically classifying objects and subsequently predict their groups and associations. This research will thus develop a new generation of AI approaches to learn the different stages of malwares and subsequently classify and predict multistage cyber attacks.

This PhD project will firstly bootstrap our group’s existing work on Generative Adversarial Network (GAN) based network intrusions classifier, and develop novel machine learning and AI approaches that could capture the multistage associations of the malware samples. Our existing models and data could be explored for an agile start. You will also learn to generate and publish datasets to promote further research and contribute to the cybersecurity research community.

The proposed research will suit a self-motivated student from the Computing, Mathematics or Engineering background, who is interested in AI, machine learning or cybersecurity. Some research and working experience on machine learning, cybersecurity or data science would be desirable. As an exciting part of this project, you will receive a unique opportunity to spend 3 months each year at the BT labs, to do research in an industrial environment and present your work to the practice.

This award provides annual funding to cover UK/EU tuition fees and a tax-free stipend. For students who pay UK/EU tuition fees the award will cover the tuition fees in full, plus at least £15,009 per year tax-free stipend.

Email Now

Insert previous message below for editing? 
You haven’t included a message. Providing a specific message means universities will take your enquiry more seriously and helps them provide the information you need.
Why not add a message here
* required field
Send a copy to me for my own records.

Your enquiry has been emailed successfully





FindAPhD. Copyright 2005-2019
All rights reserved.