Despite the impressive performance of Artificial Intelligence (AI) systems, their robustness remains elusive and constitutes a key issue that impedes large-scale adoption. Besides, robustness is interpreted differently across domains and contexts of AI. In this work, we systematically survey recent progress to provide a reconciled terminology of concepts around AI robustness. We introduce three taxonomies to organize and describe the literature both from a fundamental and applied point of view: 1) methods and approaches that address robustness in different phases of the machine learning pipeline; 2) methods improving robustness in specific model architectures, tasks, and systems; and in addition, 3) methodologies and insights around evaluating the robustness of AI systems, particularly the trade-offs with other trustworthiness properties. Finally, we identify and discuss research gaps and opportunities and give an outlook on the field. We highlight the central role of humans in evaluating and enhancing AI robustness, considering the necessary knowledge they can provide, and discuss the need for better understanding practices and developing supportive tools in the future.

尽管人工智能（AI）系统的性能令人印象深刻，但其稳健性仍然难以捉摸，并构成了阻碍大规模采用的关键问题。此外，在人工智能领域和背景下，鲁棒性的解释也不同。在这项工作中，我们系统地调查了最新进展，以提供有关人工智能鲁棒性的概念的一致术语。我们引入了三种分类法，从基础和应用的角度来组织和描述文献：1）解决机器学习流程不同阶段鲁棒性的方法和方法； 2）提高特定模型架构、任务和系统鲁棒性的方法；此外，3）围绕评估人工智能系统稳健性的方法和见解，特别是与其他可信属性的权衡。最后，我们确定并讨论研究差距和机会，并对该领域进行展望。我们强调人类在评估和增强人工智能鲁棒性方面的核心作用，考虑他们可以提供的必要知识，并讨论未来更好地理解实践和开发支持工具的必要性。