Ttraditional safety engineering is coming to a turning point moving from deterministic, non-evolving systems operating in well-defined contexts to increasingly autonomous and learning-enabled AI systems which are acting in largely unpredictable operating contexts. We outline some of underlying challenges of safe AI and suggest a rigorous engineering framework for minimizing uncertainty, thereby increasing confidence, up to tolerable levels, in the safe behavior of AI systems.
@article{arxiv.2201.10436,
title = {Safe AI -- How is this Possible?},
author = {Harald Rueß and Simon Burton},
journal= {arXiv preprint arXiv:2201.10436},
year = {2022}
}