On Safety Assessment of Artificial Intelligence
This addresses safety concerns for AI deployment in critical domains, but it is incremental as it builds on existing safety assessment frameworks.
The paper tackles the problem of safety assessment for AI systems in safety-critical applications by proposing to treat AI models as statistical models and allocate part of the safety budget for their probabilistic faulty behavior, demonstrated with a simple example.
In this paper we discuss how systems with Artificial Intelligence (AI) can undergo safety assessment. This is relevant, if AI is used in safety related applications. Taking a deeper look into AI models, we show, that many models of artificial intelligence, in particular machine learning, are statistical models. Safety assessment would then have t o concentrate on the model that is used in AI, besides the normal assessment procedure. Part of the budget of dangerous random failures for the relevant safety integrity level needs to be used for the probabilistic faulty behavior of the AI system. We demonstrate our thoughts with a simple example and propose a research challenge that may be decisive for the use of AI in safety related systems.