Defeater Cards introduce a new 5W1H-structured documentation method for systematically characterizing defeaters in safety assurance cases, supported by an open repository and demonstrated in cross-domain case studies.
Medical Journal of Australia, 181(1): 36–39
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
representative citing papers
Analysis of 499 generative AI incidents shows use-related failures predominate and frequently harm non-users, producing a distinct risk profile from traditional AI.
Systems analyses of a frontier-lab AI coding agent scenario using STECA, STPA, and FRAM reveal unverifiable governance loops, ineffective control delays, and gradual safeguard erosion, supporting the addition of systems-level methods to model-focused AI evaluations.
A framework with seven dimensions for AI incident reporting systems is developed from literature and case studies in safety-critical industries to guide institutional design choices.
The paper surveys worldwide AI regulations, risk categories, and assessment methodologies, highlighting best practices and research gaps.
citing papers explorer
-
Defeater Cards: Characterizing and Managing Safety Assurance Case Defeaters
Defeater Cards introduce a new 5W1H-structured documentation method for systematically characterizing defeaters in safety assurance cases, supported by an open repository and demonstrated in cross-domain case studies.
-
A Closer Look at the Existing Risks of Generative AI: Mapping the Who, What, and How of Real-World Incidents
Analysis of 499 generative AI incidents shows use-related failures predominate and frequently harm non-users, producing a distinct risk profile from traditional AI.
-
Exploring Systems-Thinking Approaches to Loss of Control Risk
Systems analyses of a frontier-lab AI coding agent scenario using STECA, STPA, and FRAM reveal unverifiable governance loops, ineffective control delays, and gradual safeguard erosion, supporting the addition of systems-level methods to model-focused AI evaluations.
-
Designing Incident Reporting Systems for Harms from General-Purpose AI
A framework with seven dimensions for AI incident reporting systems is developed from literature and case studies in safety-critical industries to guide institutional design choices.
-
Overview of Risk Assessment and Management for Intelligent Systems under the AI Act and Beyond
The paper surveys worldwide AI regulations, risk categories, and assessment methodologies, highlighting best practices and research gaps.