Doctoral student in Computer Science - Secure Distributed AI
About this role
Örebro University and the School of Science and Technology are looking for a doctoral student (PhD student) for the doctoral programme in Computer Science, concluding with a doctoral degree.
Start date: 1st of December 2026
Project description
The multi-disciplinary center for cyber resilient AI, RESIST, is a national effort funded by the Swedish Strategic Research Foundation (SSF) to bring together leading researchers in AI and cybersecurity to develop novel solutions to cyber resilient AI for the benefit of Swedish industry and society. The vision is to make Sweden a role model in secure trustworthy AI by pioneering cyber resilience across the AI lifecycle. The research program focuses on four key themes: Trustworthy and Verifiable AI, Runtime Security Assurance, Robust and Secure AI-Supported Development, and Resilient Distributed and Agentic AI. RESIST will drive world-class research in the intersection between AI and cybersecurity through a strong, stimulating and well-connected international research environment. Research outcomes will be validated in real-world scenarios with industry and public-sector partners. RESIST will also serve as a national hub for cyber resilient AI, promoting education, knowledge sharing, and policy development.
This PhD position is associated with the research theme Resilient Distributed and Agentic AI. For systems with multiple agents – robots, AI agents or humans, we will look at their interactions and analyze whether we can use explicit interaction protocols as a basis to secure interaction on a higher level than communication frameworks. Such high-level negotiation protocols can be pre-defined or learnt, yet they also need to capture flexibility in exchanging information or giving instructions for modelling modern multi-agent workflows. Research will concern the generation of explicit interaction protocols adapted to the agents involved, as well as the generation of execution guards from those learnt protocols. The overall g