Cyber Security is one of the critical challenges and a well-known issue in the IoT ecosystem. Due to heterogeneity and resource constraints, optimisation, testing, and validation of end-to-end systems are challenging problems that lead to insecure systems. In recent years, many machine learning and artificial intelligence (ML/AI) solutions have been investigated to overcome some of these challenges; however, these solutions are pretty application-specific and need to scale. ML/AI-based solutions for resource-constrained devices are still in the early stages and must be adequately tailored to IoT systems.
The proposed work will be based on a concrete IoT platform and a concrete cyber attack, to be surveyed and chosen by you and your advisors during the first year of study. The work will be fully supported by an experimental setup based on the simulation of large-scale networks and hardware prototyping of specific scenarios. These resources, developed over the first half of the PhD period, aim to evaluate the potential use of ML/AI techniques to detect an attack and improve network resilience. You will have the necessary tools and support to carry out your research effectively.
The core research will include the formalisation and definition of attack scenarios, the investigation of monitoring techniques and metrics of interest to support attack detection and resilience evaluation, the comparative analysis of ML/AI techniques (to be chosen by the student) and the strategies to deploy such solutions over network nodes, edge devices and cloud infrastructure. The following research questions will be addressed: What kind of data obtained from network simulation and prototypes can be used to train ML/AI techniques? What are the biases, and how can they be avoided? How accurate are those techniques when detecting attacks, and how effective are they in increasing the network resilience to those attacks? Which deployment strategy provides the best trade-off between detection accuracy, resilience, and network overheads?
This plan provides a well-delimited area within the IoT research landscape, offering a solid foundation for your research. But it also allows you the freedom to choose an IoT cybersecurity problem that is industry-relevant and amenable to the application of ML/AI solutions. This flexibility empowers you to shape your research and make a significant contribution to the field.
Funding Details
The successful candidate will receive:
- Full tuition fee waiver (home student fees covered).
- An annual stipend to cover living expenses.
- Research expenses for conducting the two use-case studies.
- Travel funds to present findings at international conferences and workshops.
Eligibility Criteria
Applicants must:
- Hold a Master’s degree in Computer Science, Electronics Engineering, or a related field.
- Have a strong background in network communication, IoT technologies, cyber security and embedded systems.
- Demonstrate proficiency in programming and experience with open-source software development.
- Exhibit strong analytical and problem-solving skills.
Application Process
Interested candidates should submit the following documents:
- A detailed CV.
- A cover letter explaining their interest in the project and relevant experience.
- Academic transcripts.
- Contact information for at least two academic referees.
- A research proposal outlining their approach to achieving the project objectives (max 2 pages).
Candidates must apply for a PhD in Computer Science at the University of York and quote this research project on the application. Find out more here at: https://www.york.ac.uk/study/postgraduate-research/apply/
Application Deadline
Applications are accepted all year round. Find out more here at: https://www.york.ac.uk/study/postgraduate-research/apply/
Contact Information
Enquiries: For further information, please contact Dr Poonam Yadav, email: poonam.yadav@york.ac.uk.