PhD Studentship in Computer Science: Edge-AI enabled multi-modal robotic sensing platforms for adversarial settings

About the Project

Award summary

100% home fees covered, and a minimum tax-free annual living allowance of £21,805 (2026-27 UKRI rates).

Overview

The convergence of advanced AI agentic models with physical robotics introduces a complex, multi-layered attack surface. Vulnerabilities exist in hardware, firmware, on-device APIs, cloud/edge channels, and decision-making logic. The project involves multi-modal robot construction (air and sea), building edge intelligence for tough environments (wind, waves, flow) such as coastal surveys with degraded vision and intermittent communication. It supports any aspect of an end-to-end secure software stack for AI-powered robotics, focusing on a resilient 'secure API ecosystem' bridging on-device and cloud-based models, prioritizing proactive hardening and safe innovation. The core hypothesis: a security-by-design, developer-centric framework enhances robotic agent resilience against advanced threats while fostering a third-party ecosystem. Current research siloes hardware security, network security, and AI safety, lacking holistic frameworks from MCU to large AI models, introducing critical security challenges:

• Expanded Attack Surface: APIs/SDKs become prime targets for injection, privilege escalation, and data theft.
• On-Device Risks: Physical/side-channel attacks on sensors can corrupt model integrity and cause unsafe actions.
• AI-Specific Threats: Adversarial attacks on perception/policy models may trigger catastrophic failures.
• Scalability vs. Security: Fast iteration of agentic models outpaces robust security controls.

Number of awards

1

Start date

September 2026

Award duration

3.5 Years

Application closing date

15 June 2026

Sponsor

School of Computing, Newcastle University

Name of supervisor/s

Prof S Nagaraja

Dr M Ahmed

Eligibility Criteria

You must have, or expect to gain, a minimum 2:1 Honours degree or international equivalent in a relevant subject or subject relevant to the proposed PhD project. Enthusiasm for research, the ability to think and work independently, excellent analytical skills and strong verbal and written communication skills are also essential requirements.

The studentship covers fees at Home rate (UK and EU applicants with pre-settled/settled status and meet the residency criteria). International applicants are welcome but must cover the difference between Home and International fees.

Applicants whose first language is not English require an IELTS score of 6.5 overall with a minimum of 5.5 in all sub-skills.

International applicants may require an ATAS (Academic Technology Approval Scheme) clearance certificate prior to obtaining their visa and to study on this programme.

How to apply

Apply using Newcastle Portal

Once registered select ‘Create a Postgraduate Application’.

‘Course Search’ to identify programme of study:

• search for the ‘Course Title’ using the programme code: 8050F
• Research Area: Computing Science
• Select ‘PhD Computer Science (Full Time) – Computing Science as programme of study

Provide the following information in the ‘Further Questions’ section:

• ‘Personal Statement’ (mandatory field) - upload a document/write statement directly into the application form
• studentship code COMP2178 in ‘Studentship/Partnership Reference’ field
• when prompted for how you are providing your research proposal - select ‘Write Proposal’. Then type in title of the research project from advert – then provide your own statement.