Quantitative AI risk assessment: a starting point
Current AI risk management relies on qualitative approaches, much like nuclear safety before 1975. We propose a shift to quantitative risk modeling, following the approach that transformed nuclear safety. We propose a methodology and demonstrate it by building nine probabilistic models of AI-enabled cyber attacks. This is a first attempt at AI risk quantification. We invite criticism and hope this can be a starting point for the kind of iterative improvement that made nuclear safety robust.Intro
By Henry Papadatos