<p>This document surveys topics related to trustworthiness in AI systems, including the following:</p>
<p>— approaches to establish trust in AI systems through transparency, explainability, controllability, etc.;</p>
<p>— engineering pitfalls and typical associated threats and risks to AI systems, along with possible mitigation techniques and methods; and</p>
<p>— approaches to assess and achieve availability, resiliency, reliability, accuracy, safety, security and privacy of AI systems.</p>
<p>The specification of levels of trustworthiness for AI systems is out of the scope of this document.</p>
Registration number (WIID)
77608
Scope
<p>This document surveys topics related to trustworthiness in AI systems, including the following:</p>
<p>— approaches to establish trust in AI systems through transparency, explainability, controllability, etc.;</p>
<p>— engineering pitfalls and typical associated threats and risks to AI systems, along with possible mitigation techniques and methods; and</p>
<p>— approaches to assess and achieve availability, resiliency, reliability, accuracy, safety, security and privacy of AI systems.</p>
<p>The specification of levels of trustworthiness for AI systems is out of the scope of this document.</p>
