arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2110.01167cs.AIcs.LG
收藏

值得信赖的AI:从原则到实践

Trustworthy AI: From Principles to Practices

JD AI Research(京东人工智能研究院)

Bo Li, Peng Qi, Bo Liu, Shuai Di, Jingen Liu, Jiquan Pei, Jinfeng Yi, Bowen Zhou

摘要:

人工智能(Artificial Intelligence,AI)技术的快速发展使得各种基于AI的系统得以部署,但目前的AI系统存在易受不可感知攻击、对弱势群体有偏见、缺乏用户隐私保护等问题。这些缺点降低了用户体验,侵蚀了人们对所有AI系统的信任。在这篇综述中,我们为人工智能从业者提供了一个构建值得信赖的人工智能系统的全面指南。我们首先介绍了人工智能可信度重要方面的理论框架,包括鲁棒性,泛化性,可解释性,透明度,可重复性,公平性,隐私保护和问责制。为了将目前可用但分散的方法统一到值得信赖的人工智能中,我们将它们组织成一种系统化的方法,考虑人工智能系统的整个生命周期,从数据采集到模型开发,再到系统开发和部署,最后到持续监控和治理。在此框架内,我们为从业者和社会利益相关者提供了具体的行动项目(例如,研究人员、工程师和监管机构)来提高人工智能的可信度。最后,我们确定了值得信赖的人工智能系统未来发展的关键机遇和挑战,我们确定了向全面值得信赖的人工智能系统转变的必要性。

英文摘要:

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.

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。

↑