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.
翻译:人工智能(AI)技术的迅速发展使基于它的各种系统得以部署。然而,许多现有的人工智能系统被认为容易受到无法察觉的攻击,对代表性不足的群体有偏见,缺乏用户的隐私保护。这些缺陷削弱了用户的经验,侵蚀了人们对所有人工智能系统的信任。在本次审查中,我们向AI从业者提供了建立可信赖的人工智能系统的全面指南。我们首先引入了AI可信赖性重要方面的理论框架,包括稳健性、普遍性、可解释性、透明度、可重复性、公平性、隐私保护和问责制。为了统一目前现有的但零散的方法,争取可靠的AI,我们将这些系统组织起来时采用了系统化的方法,考虑到AI系统的整个生命周期,从数据获取到模型开发、系统开发和部署,到系统开发和部署,最后是持续监测和治理。在这个框架内,我们为实践者和社会利益攸关方(例如研究人员、工程师和监管者)提供了具体行动项目,以提高AI的可信度。最后,我们确定了今后发展可靠的人工智能系统的主要机会和挑战。我们确定需要将范式转向全面可靠的AI系统。