1 Scope
This document surveys topics related to trustworthiness in AIsystems, including the following:
-
— approaches to establish trust in AIsystems through transparency, explainability, controllability, etc.;
-
— engineering pitfalls and typical associated threats and risks to AIsystems, along with possible mitigation techniques and methods; and
-
— approaches to assess and achieve availability, resiliency, reliability, accuracy, safety, security and privacy of AIsystems.
The specification of levels of trustworthiness for AIsystems is out of the scope of this document.