可信机器学习技术：社会技术背景下的调查
Technologies for Trustworthy Machine Learning: A Survey in a Socio-Technical Context
摘要：
对基于人工智能的服务和系统的社会影响的担忧鼓励世界各地的政府和其他组织提出人工智能政策框架，以解决公平，问责制，透明度和相关主题。为了实现这些框架的目标，构建机器学习系统的数据和软件工程师需要了解各种相关的支持工具和技术。在本文中，我们概述了支持构建可信机器学习系统的技术，即，系统的属性证明人们信任它们。我们认为，四类系统属性有助于实现政策目标，即公平性，可解释性，可解释性和安全性（FEAS）。我们将讨论如何在机器学习生存周期的所有阶段（从数据汇集到运行时模型推理）中考虑这些属性。因此，我们在本文中调查的主要技术方面的所有四个FEAS属性，以数据为中心，以及以模型为中心的阶段的机器学习系统生存周期。最后，我们确定了开放的研究问题，特别关注值得信赖的机器学习技术及其对个人和社会的影响之间的联系。
英文摘要：
Concerns about the societal impact of AI-based services and systems has encouraged governments and other organisations around the world to propose AI policy frameworks to address fairness, accountability, transparency and related topics. To achieve the objectives of these frameworks, the data and software engineers who build machine-learning systems require knowledge about a variety of relevant supporting tools and techniques. In this paper we provide an overview of technologies that support building trustworthy machine learning systems, i.e., systems whose properties justify that people place trust in them. We argue that four categories of system properties are instrumental in achieving the policy objectives, namely fairness, explainability, auditability and safety & security (FEAS). We discuss how these properties need to be considered across all stages of the machine learning life cycle, from data collection through run-time model inference. As a consequence, we survey in this paper the main technologies with respect to all four of the FEAS properties, for data-centric as well as model-centric stages of the machine learning system life cycle. We conclude with an identification of open research problems, with a particular focus on the connection between trustworthy machine learning technologies and their implications for individuals and society.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
