Funding

Self-funded

Project code

CMP10271026

Start dates

October, February and April

Application deadline

Applications accepted all year round

Applications are invited for a self-funded, 3-year full-time or 6-year part time PhD project.

The PhD will be based in the School of Computing and will be supervised by Dr Rinat Khusainov and Dr Eslam Amer.

The work on this project will:

 

  • Analyse adversarial attack strategies against LLM-based malware detection
  • Develop robust defences for malware classification and reverse engineering tasks
  • Design automated adversarial malware generation pipelines
  • Create evaluation benchmarks for adversarial robustness in malware analysis
  • Quantify risks of model evasion, poisoning, and data leakage in malware detection
  • Release reproducible datasets and tools to support secure malware research

Large Language Models (LLMs) are increasingly used in cybersecurity, including malware analysis, detection, and reverse engineering. However, these models are vulnerable to adversarial attacks. Carefully crafted malicious inputs can evade detection, manipulate classification outcomes, or extract sensitive information. Such vulnerabilities present significant risks in security-critical domains.

This PhD project will investigate adversarial attack strategies in the context of malware analysis with LLMs. The research will examine evasion techniques, adversarial code modifications, and poisoning of malware datasets. It will also design robust defences, such as adversarial training, input validation, anomaly detection, and secure model evaluation frameworks.

The aim is to understand the limitations of current LLM-based malware analysis systems under adversarial pressure, and to propose scalable methods to improve their reliability. The project will combine theoretical insights with practical experiments on real-world malware datasets and simulated attack scenarios.

The successful candidate will join a research team with expertise in AI security, malware detection, and natural language processing. The School provides access to advanced computing resources, including the Sciama supercomputer, and fosters a strong, collaborative research environment.

 

Fees and funding

Visit the research subject area page for fees and funding information for this project.

Funding availability: Self-funded PhD students only. 

PhD full-time and part-time courses are eligible for the UK  (UK and EU students only).

 

Bench fees

Some PhD projects may include additional fees – known as bench fees – for equipment and other consumables, and these will be added to your standard tuition fee. Speak to the supervisory team during your interview about any additional fees you may have to pay. Please note, bench fees are not eligible for discounts and are non-refundable.

Entry requirements

You'll need a good first degree from an internationally recognised university (minimum upper second class or equivalent, depending on your chosen course) or a master’s degree in computer science or a related area. In exceptional cases, we may consider equivalent professional experience and/or Qualifications.

English language proficiency at a minimum of IELTS band 6.5 with no component score below 6.0.

 

  • Strong programming and numeracy skills.
  • Background in cybersecurity or malware analysis is desirable.
  • Knowledge of machine learning and natural language processing.
  • Familiarity with adversarial machine learning or security aspects of AI.
  • Ability to design, test, and evaluate attacks and defences for malware analysis systems.

 

 

How to apply

We’d encourage you to contact Dr Rinat Khusainov (rinat.khusainov@port.ac.uk) to discuss your interest before you apply, quoting the project code.

When you are ready to apply, please follow the 'Apply now' link on the Computing PhD subject area page and select the link for the relevant intake. Make sure you submit a personal statement, proof of your degrees and grades, details of two referees, proof of your English language proficiency and an up-to-date CV. Our ‘How to Apply’ page offers further guidance on the PhD application process. 

When applying please quote project code: CMP10271026