可信人工智能系统的质量属性与实现:三级研究  

Quality Attributes and Practices of Trustworthy Artificial Intelligence Systems:A Tertiary Study

作　　者：李功源 刘博涵 杨雨豪 邵栋[1,2] LI Gong-Yuan;LIU Bo-Han;YANG Yu-Hao;SHAO Dong(Software Institute,Nanjing University,Nanjing 210023,China;State Key Laboratory for Novel Software Technology(Nanjing University),Nanjing 210023,China)

机构地区：[1]南京大学软件学院,江苏南京210023 [2]计算机软件新技术国家重点实验室(南京大学),江苏南京210023

出　　处：《软件学报》2023年第9期3941-3965,共25页Journal of Software

基　　金：国家自然科学基金(62072227,62202219);国家重点研发计划(2019YFE0105500);江苏省重点研发计划(BE2021002-2);南京大学计算机软件新技术国家重点实验室创新项目(ZZKT2022A25);海外开放课题(KFKT2022A09)。

摘　　要：人工智能系统以一种前所未有的方式,被广泛地用于解决现实世界的各种挑战,其已然成为推动人类社会发展的核心驱动力.随着人工智能系统在各行各业的迅速普及,人们对人工智能系统的可信性愈发感到担忧,其主要原因在于,传统软件系统的可信性已不足以完全描述人工智能系统的可信性.对于人工智能系统的可信性的研究,具有迫切需要.目前已有大量相关研究,且各有侧重,但缺乏一个整体性、系统性的认识.研究是一项以现有二级研究为研究对象的三级研究,旨在揭示人工智能系统的可信性相关的质量属性和实践的研究现状,建立一个更加全面的可信人工智能系统质量属性框架.收集、整理和分析2022年3月前发表的34项二级研究,识别21种与可信性相关的质量属性及可信性的度量方法和保障实践.研究发现,现有研究主要关注在安全性和隐私性上,对于其他质量属性缺乏广泛且深入的研究.对于需要跨学科协作的两个研究方向,需要在未来的研究中引起重视,一方面是人工智能系统本质上还是一个软件系统,其作为一个软件系统的可信值得人工智能和软件工程专家合作研究;另一方面,人工智能是人类对于机器拟人化的探索,如何从系统层面保障机器在社会环境下的可信,如怎样满足人本主义,值得人工智能和社会科学专家合作研究.Artificial intelligence systems are widely used to solve various challenges in the real world in an unprecedented way,and they have become the core driving force for the development of human society.With the rapid popularization of artificial intelligence systems in all walks of life,the trustworthiness of artificial intelligence systems is becoming more and more worrying.The main reason is that the trustworthiness of traditional software systems is not enough to fully describe that of artificial intelligence systems.Therefore,research on the trustworthiness of artificial intelligence systems is urgently needed.At present,there have been a large number of relevant studies,which focus on different aspects.However,these studies lack a holistic and systematic understanding.This study is a tertiary study with the existing secondary study as the research object.It aims to reveal the research status of quality attributes and practices related to the trustworthiness of artificial intelligence systems and establish a more comprehensive quality attribute framework for trustworthy artificial intelligence systems.This study collects,sorts out,and analyzes 34 secondary studies published until March 2022.In addition,it identifies 21 quality attributes related to trustworthiness,as well as measurement methods and assurance practices of trustworthiness.The study finds that existing research mainly focuses on security and privacy,and extensive and in-depth research on other quality attributes is fewer.Furthermore,two research directions requiring interdisciplinary collaboration need more attention in future research.On the one hand,the artificial intelligence system is essentially a software system,and its trustworthiness as a software system is worthy of collaborative research by artificial intelligence and software engineering experts.On the other hand,artificial intelligence belongs to human’s exploration of machine anthropomorphism,and research on how to ensure the trustworthiness of machines in the social environment from

关 键 词：人工智能系统 可信 质量属性 实践 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]