System Assurance in The Era of Large Language Models (LLMs)
June 29 @ 2:00 pm - 3:00 pm
[]
Join the IEEE Toronto Instrumentation & Measurement – Robotics & Automation Joint Chapter for a technical talk presented by Dr. Alvine B. Belle from York <a href="http://University.
Monday” target=”_blank” title=”University.
Monday”>University.
Monday, June 29, 2026 @ 2:00 – 3:00 PM (EST)
Abstract:
Justifying the correct implementation of the non-functional requirements (e.g., safety, security, reliability) of mission-critical systems is crucial to prevent system failure. The latter could have severe consequences such as the death of people, financial losses, and environmental damage. Assurance cases (e.g., safety cases, security cases) can be used to prevent system failure. They therefore support system assurance. Assurance cases are structured sets of arguments supported by evidence and aiming at demonstrating that a system’s non-functional requirements have been correctly implemented. However, although the availability of complete assurance cases is crucial to allow the research community to contribute to the system assurance field, it remains very challenging to access complete assurance cases due to several concerns such as confidentiality issues. Furthermore, assurance cases are usually very large documents. Still, their creation remains a manual, labor-intensive, and error-prone process that heavily relies on domain expertise. Therefore, relying on (semi-)automated techniques such as those supported by generative AI through LLMs (Large Language Models) could alleviate the task of assurance case developers by facilitating the execution of all activities related to the assurance case <a href="http://lifecycle.
In” target=”_blank” title=”lifecycle.
In”>lifecycle.
In this talk, Dr. Belle will present the current solutions on LLM-based system assurance to inform future research on this topic. She will illustrate these solutions with various case studies spanning several application domains (e.g., healthcare, automotive, and nuclear).
Speaker(s): Alvine B. Belle, PhD,