Landscape of AI safety concerns -- A methodology to support safety assurance for AI-based autonomous systems
This addresses the problem of safety assurance for engineers and regulators in autonomous systems, but it is incremental as it builds upon existing ideas for analyzing AI safety concerns.
The paper tackles the challenge of assuring safety in AI-based autonomous systems by proposing the Landscape of AI Safety Concerns methodology, which systematically demonstrates the absence of AI-specific insufficiencies to support safety assurance cases, as illustrated in a case study with a driverless regional train.
Artificial Intelligence (AI) has emerged as a key technology, driving advancements across a range of applications. Its integration into modern autonomous systems requires assuring safety. However, the challenge of assuring safety in systems that incorporate AI components is substantial. The lack of concrete specifications, and also the complexity of both the operational environment and the system itself, leads to various aspects of uncertain behavior and complicates the derivation of convincing evidence for system safety. Nonetheless, scholars proposed to thoroughly analyze and mitigate AI-specific insufficiencies, so-called AI safety concerns, which yields essential evidence supporting a convincing assurance case. In this paper, we build upon this idea and propose the so-called Landscape of AI Safety Concerns, a novel methodology designed to support the creation of safety assurance cases for AI-based systems by systematically demonstrating the absence of AI safety concerns. The methodology's application is illustrated through a case study involving a driverless regional train, demonstrating its practicality and effectiveness.