arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2210.08906cs.AI
收藏

A.I.鲁棒性:以人为本的技术挑战和机遇视角

A.I. Robustness: a Human-Centered Perspective on Technological Challenges and Opportunities

Politecnico di Milano(米兰理工大学);Delft University of Technology(代尔夫特理工大学)

Andrea Tocchetti, Lorenzo Corti, Agathe Balayn, Mireia Yurrita, Philip Lippmann, Marco Brambilla, Jie Yang

摘要:

尽管人工智能(AI)系统的性能令人印象深刻,但其鲁棒性仍然难以捉摸,并构成了阻碍大规模采用的关键问题。鲁棒性已经在人工智能的许多领域进行了研究,但在不同的领域和背景下有不同的解释。在这项工作中,我们系统地调查了最近的进展,以提供关于AI鲁棒性的概念的协调术语。我们介绍了三个分类来组织和描述文献,从基础和应用的角度来看:1)鲁棒性的方法和方法在不同阶段的机器学习管道; 2)鲁棒性的特定模型架构,任务和系统;此外,3)鲁棒性评估方法和见解,特别是权衡与其他可信度属性。最后,我们确定并讨论了研究差距和机会,并对该领域进行了展望。我们强调了人类在评估和增强人工智能鲁棒性方面的核心作用,考虑了人类可以提供的必要知识,并讨论了未来更好地理解实践和开发支持工具的必要性。

英文摘要:

Despite the impressive performance of Artificial Intelligence (AI) systems, their robustness remains elusive and constitutes a key issue that impedes large-scale adoption. Robustness has been studied in many domains of AI, yet with different interpretations across domains and contexts. In this work, we systematically survey the 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) robustness by methods and approaches in different phases of the machine learning pipeline; 2) robustness for specific model architectures, tasks, and systems; and in addition, 3) robustness assessment methodologies and insights, 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 humans can provide, and discuss the need for better understanding practices and developing supportive tools in the future.

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。

↑