4 papers
CUBICS: Situation-aware performance estimation for safety-relevant ML components
Benjamin Herd, Jessica Kelly, Mario Trapp
Machine learning (ML) is a key technology driving innovation today, but ensuring ML safety remains a major challenge for safety-related applications. A promising idea is to build p…
A Subjective Logic-based method for runtime confidence updates in safety arguments
Benjamin Herd, Jessica Kelly, Clarissa Heinemann +1
We present a method for dynamic quantitative assurance that enhances static safety cases with continuous, runtime-driven confidence updates. The method quantifies and propagates co…
Towards a compositional semantics for quantitative confidence assessment in assurance arguments
Benjamin Herd, Jessica Kelly, Jan Sabsch +1
Assurance arguments provide a clear and structured way to explain why stakeholders should trust that a system satisfies certain properties, yet widely used notations, e.g.Goal Stru…
Navigating the EU AI Act: A Methodological Approach to Compliance for Safety-critical Products
J. Kelly, S. Zafar, L. Heidemann +3
In December 2023, the European Parliament provisionally agreed on the EU AI Act. This unprecedented regulatory framework for AI systems lays out guidelines to ensure the safety, le…