A Fuzzy Approach to the Specification, Verification and Validation of Risk-Based Ethical Decision Making Models
This addresses the problem of establishing clear standards for ethical AI systems, particularly in high-stakes domains like medicine, though it appears incremental as it builds on existing fuzzy logic and risk assessment techniques.
The paper tackles the challenge of evaluating moral machines by presenting a formal method for specifying ethical decision-making models based on risk assessment, using fuzzy rules and fuzzy Petri nets for verification and validation, with a medical case study as illustration.
The ontological and epistemic complexities inherent in the moral domain make it challenging to establish clear standards for evaluating the performance of a moral machine. In this paper, we present a formal method to describe Ethical Decision Making models based on ethical risk assessment. Then, we show how these models that are specified as fuzzy rules can be verified and validated using fuzzy Petri nets. A case study from the medical field is considered to illustrate the proposed approach.