Malicious network activity detection studentship

The studentship will involve gaining an understanding of ML-based cyber-defence tools and developing novel Bayesian inference algorithms for the assessment of ML-based cyber-defence tools.

Overview

Applications are invited for a PhD studentship in the Department of Computer Science. The successful candidate will have the opportunity to develop, and apply, sophisticated (Bayesian) statistical techniques for assessing machine learning (ML)-based cyber-defence tools.

The societal impact of successful cyber-attacks is significant, costing upwards of $6 trillion a year and rising. To thwart the insidious attack methods employed by cyber-criminals, ML tools are increasingly being adopted in detecting malicious activity on computer networks.

Before such tools can be deployed on a live security-critical network -- i.e. a network for which security breaches may significantly harm its users -- the tools must be shown to provide the required level of security.

However, such demonstrations are challenging to carry out in practice because of many uncertainties; such as uncertainty about the reliability of the tools, and uncertainty about the cyber-attacks the tools will face in operation.

The PhD will involve:

1. gaining an excellent understanding of ML-based cyber-defence tools;
2. acquiring intimate knowledge of several ML/Deep learning algorithms; and
3. developing novel Bayesian inference algorithms for the assessment of ML-based cyber-defence tools.

The PhD candidate will gain an in-depth understanding of the statistical performance characteristics of these defence tools. The Bayesian methods developed will involve constrained multi-objective mathematical optimisation and advanced probability theory.

The research will also entail a significant amount of programming using Python and deep learning frameworks.

The results of the research will be of interest to organisations and institutions employing ML for cyber-defence. The skillset gained by the PhD candidate will be highly desirable in either industry or academia.

Eligibility and requirements

The candidate should have an upper second class honours BSc (or equivalent, or higher) degree in Computer Science, Statistics, Mathematics or other numerate discipline. They should demonstrate aptitude for original research.

Applicants should demonstrate experience with applying deep learning algorithms (e.g. LSTMs, RNNs), applying Bayesian inference, and programming in Python.

Applicants who also demonstrate the following will be favoured:

1. a very good understanding of probability theory and random processes;
2. significant experience with either R, Maple, or Mathematica.

A doctoral candidate is expected to meet the following pre-requisites for their PhD:

1. Demonstrate a sound knowledge of their research area
2. Achieve and demonstrate significant depth in at least a few chosen sub-areas relevant to their primary research area
3. Demonstrate the ability to conduct independent research, including a critical assessment of their own and others’ research

Previous publications in high-quality papers in reputable peer-reviewed conferences and journals are desirable.

Funding

The studentship is for 3 years and will provide full coverage of tuition fees (Home and Overseas) and an annual tax-free stipend of £12,000.

Each student would also have the opportunity to earn around £2.2K pa on an average (max. is around £4.3K pa) through a teaching assistantship. We shall prioritise these scholarship holders while allocating the teaching assistantships.

How to apply

Initial informal enquiries should be addressed to Dr. Kizito Salako.

• Email Dr. Kizito Salako

Visit our Computer science research degrees web page for further information on making a formal application.

When submitting your application, enter the title “Conservative Bayesian Assessment of Classifiers used for Malicious Network Activity Detection” and you will automatically be considered for this studentship.

You do not need to submit a proposal as part of your application as the project has already been outlined.

The online application can be found in the ‘How to apply section’ in the web link above and should include the following supporting documents:

• Copies of Degree Certificates and Transcripts in official English translation - original will be requested before an offer is made.
• Official work e-mail addresses (not private ones) for two referees (one of which must be an academic).
• Proof of English Language proficiency (minimum average score of 6.5 IELTS, with a minimum of 6.0 in each of the four components) if English is not your first language.
• Passport.

The outcome of the selection process should be announced by the end of June. The successful candidate will formally start their doctorate either in July or in October 2022.

For queries regarding the application process, please email the School.

Equality, diversity and inclusion

City, University of London is committed to promoting equality, diversity and inclusion in all its activities, processes, and culture, for our whole community, including staff, students and visitors.

We welcome applications regardless of gender, sexual orientation, disability, marital status, race, nationality, ethnic origin, religion or social class. For more information on our approaches to encouraging an inclusive environment, please see our Equality, Diversity and Inclusion pages.