信息技术.人工智能.人工智能中的可信度概述

[中文适用范围]： 本文档探讨了与人工智能系统可信度相关的主题，包括：通过透明度、可解释性、可控性等建立人工智能系统信任的方法；人工智能系统的工程陷阱、典型相关威胁和风险，以及可能的缓解技术和方法；以及评估和实现人工智能系统可用性、弹性、可靠性、准确性、安全性、保密性和隐私性的方法。人工智能系统可信度等级的规范不在本文档的讨论范围内。 [外文原描述]： This document surveys topics related to trustworthiness in AI systems, including the following: — approaches to establish trust in AI systems through transparency, explainability, controllability, etc.; — engineering pitfalls and typical associated threats and risks to AI systems, along with possible mitigation techniques and methods; and — approaches to assess and achieve availability, resiliency, reliability, accuracy, safety, security and privacy of AI systems. The specification of levels of trustworthiness for AI systems is out of the scope of this document.