The rapid development of Artificial Intelligence (AI) technology has enabled the deployment of various systems based on it. However, many current AI systems are found vulnerable to imperceptible attacks, biased against underrepresented groups, lacking in user privacy protection. These shortcomings degrade user experience and erode people's trust in all AI systems. In this review, we provide AI practitioners with a comprehensive guide for building trustworthy AI systems. We first introduce the theoretical framework of important aspects of AI trustworthiness, including robustness, generalization, explainability, transparency, reproducibility, fairness, privacy preservation, and accountability. To unify currently available but fragmented approaches toward trustworthy AI, we organize them in a systematic approach that considers the entire lifecycle of AI systems, ranging from data acquisition to model development, to system development and deployment, finally to continuous monitoring and governance. In this framework, we offer concrete action items for practitioners and societal stakeholders (e.g., researchers, engineers, and regulators) to improve AI trustworthiness. Finally, we identify key opportunities and challenges for the future development of trustworthy AI systems, where we identify the need for a paradigm shift toward comprehensively trustworthy AI systems.
Trustworthy AI in practice: an analysis of practitioners' needs and challenges
University of Bari "A. Moro"(巴里大学);Ser&Practices Srl(Ser&Practices有限公司);Pontifical Catholic University of Rio de Janeiro (PUC-Rio)(里约热内卢天主教大学);Scuola IMT Alti Studi Lucca(卢卡高等研究院)
Towards Trustworthy Physical Intelligence: From Theory to Practice Across Life Cycle
Case Western Reserve University(凯斯西储大学);Shanghai Jiao Tong University(上海交通大学);Massachusetts Institute of Technology(麻省理工学院);Columbia University(哥伦比亚大学);University of California, Riverside(加州大学河滨分校);Nanyang Technological University(南洋理工大学);New York University(纽约大学);Salesforce(Salesforce公司);Harvard University(哈佛大学);Stanford University(斯坦福大学)
Connecting the Dots in Trustworthy Artificial Intelligence: From AI Principles, Ethics, and Key Requirements to Responsible AI Systems and Regulation
University of Granada(格拉纳达大学);DaSCI Andalusian Institute in Data Science and Computational Intelligence(安达卢西亚数据科学与计算智能研究所(DaSCI));TECNALIA(泰克纳利亚研究中心);Basque Research and Technology Alliance (BRTA)(巴斯克研究与技术联盟(BRTA));University of the Basque Country (UPV/EHU)(巴斯克大学(UPV/EHU));University of Vienna(维也纳大学);Cornell University(康奈尔大学);ADIA Lab(阿布扎比投资局实验室);Khalifa University of Science and Technology(哈利法科技大学)
Bridging the Communication Gap: Evaluating AI Labeling Practices for Trustworthy AI Development
Lamarr Institute for ML and AI(拉马尔机器学习与人工智能研究所);TU Dortmund University(多特蒙德工业大学);RC Trustworthy Data Science and Security(可信数据科学与安全研究中心);Enterprise Computing(企业计算机构);Smart City Science(智慧城市科学机构)
Causality Is Key to Understand and Balance Multiple Goals in Trustworthy ML and Foundation Models
CISPA Helmholtz Center for Information Security(CISPA海德堡信息安全中心);Max Planck Institute for Intelligent Systems, Tübingen(马克斯·普朗克智能系统研究所(图宾根));Google Research(谷歌研究);ETH Zürich(苏黎世联邦理工学院);University of Toronto(多伦多大学)
FUTURE-AI: Guiding Principles and Consensus Recommendations for Trustworthy Artificial Intelligence in Medical Imaging
Barcelona Artificial Intelligence in Medicine Lab (BCN-AIM)(巴塞罗那医学人工智能实验室(BCN-AIM));Maggioli SPA(马焦利股份公司);Fundació TIC Salut i Social(信息与通信技术社会基金会);Generalitat de Catalunya(加泰罗尼亚政府);Hospital Universitario y Politécnico La Fe(拉费大学及综合医院);Health Research Institute(健康研究所);Foundation for Research and Technology(研究与技术基金会);National Research Council(国家研究委员会);Maastricht University(马斯特里赫特大学)
A roadmap to fair and trustworthy prediction model validation in healthcare
Duke-NUS Medical School(杜克-国大医学院);Erasmus MC University Medical Center(伊拉斯姆斯大学医学中心);Singapore Health Services(新加坡保健服务集团);Singapore General Hospital(新加坡中央医院);Duke University(杜克大学);National University of Singapore(新加坡国立大学)
A Design Framework for operationalizing Trustworthy Artificial Intelligence in Healthcare: Requirements, Tradeoffs and Challenges for its Clinical Adoption
organization= Faculty of Medicine;Health Technology, Tampere University , city= Tampere , postcode= 33100 , country= Finland;organization= TECNALIA, Basque Research \& Technology Alliance (BRTA) , city= Derio , postcode= 48160 , country= Spain;organization= Department of Mathematics, University of the Basque Country (UPV/EHU) , city= Leioa , postcode= 48940 , country= Spain;organization= Tampere Heart Hospital, Tampere University Hospital , city= Tampere , postcode= 33520 , country= Finland
OpenAI;McGill University(麦吉尔大学);Mila(米拉人工智能研究院);Centre for the Governance of AI(人工智能治理中心);Department of Engineering Science, University of Oxford(牛津大学工程科学系)
Towards Trustworthy and Aligned Machine Learning: A Data-centric Survey with Causality Perspectives
Bundelkhand Institute of Engineering and Technology(本德尔坎德工程技术学院);Nanyang Technological University(南洋理工大学);University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校)
A Checklist for Trustworthy, Safe, and User-Friendly Mental Health Chatbots
University of Illinois Urbana-Champaign, Urbana, United States(伊利诺伊大学厄巴纳-香槟分校);Indiana University Indianapolis, Indianapolis, United States(印第安纳大学印第安纳波利斯分校)
Advancing Trustworthy AI for Sustainable Development: Recommendations for Standardising AI Incident Reporting
Telecommunication Engineering Centre, Ministry of Communications(通信部电信工程中心);Defence Institute of Advanced Technology, Ministry of Defence(国防部高级国防技术研究院)