CoDefeater: Using LLMs To Find Defeaters in Assurance Cases
Preprint
Abstract
Constructing assurance cases is a widely used, and sometimes required, process toward demonstrating that safety-critical systems will operate safely in their planned environment. To mitigate the risk of errors and missing edge cases, the concept of defeaters - arguments or evidence that challenge claims in an assurance case - has been introduced. Defeaters can provide timely detection of weaknesses in the arguments, prompting further investigation and timely mitigations. However, capturing defeaters relies on expert judgment, experience, and creativity and must be done iteratively due to evolving requirements and regulations. This paper proposes CoDefeater, an automated process to leverage large language models (LLMs) for finding defeaters. Initial results on two systems show that LLMs can efficiently find known and unforeseen feasible defeaters to support safety analysts in enhancing the completeness and confidence of assurance cases.Keywords
All Related Versions
This publication has 19 references indexed in Scilit:
- Assessing the Usefulness of Assurance Cases: Experience With the Large Hadron ColliderSystems Engineering, 2025
- Prompt-Enhanced Software Vulnerability Detection Using ChatGPT2024
- CLARISSA: Foundations, Tools & Automation for Assurance Cases2023
- A Survey of Tool-supported Assurance Case Assessment TechniquesACM Computing Surveys, 2019
- Preventing Omission of Key Evidence Fallacy in Process-Based Argumentations2018
- Medical cyber-physical systems: A surveyJournal of Medical Systems, 2018
- A model management approach for assurance case reuse due to system evolution2016
- An extended systematic literature review on provision of evidence for safety certificationInformation and Software Technology, 2014
- ISO 26262 safety cases: compliance and assurance2011
- Critical system properties: survey and taxonomyReliability Engineering & System Safety, 1994