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 2304.08275cs.CYcs.AI
收藏

实施负责任的AI:伦理维度之间的张力与权衡

Implementing Responsible AI: Tensions and Trade-Offs Between Ethics Aspects

Data61 / CSIRO(Data61 / 联邦科学与工业研究组织);Griffith University(格里菲斯大学)

Conrad Sanderson, David Douglas, Qinghua Lu

AI总结:

本文梳理负责任AI伦理原则中隐私、准确性、公平性等维度的冲突,提出包含10项张力与权衡的目录,以辅助开发者作出有据可依的实践判断。

摘要:

为缓解人们对AI/ML系统被误用和滥用的担忧,许多面向负责任AI的伦理原则集已被提出。这些原则集的底层维度包括隐私、准确性、公平性、鲁棒性、可解释性和透明度。然而,这些维度之间存在潜在张力,给试图遵循这些原则的AI/ML开发者带来困难。例如,提高AI/ML系统的准确性可能会降低其可解释性。作为将这些原则落实到实践中的持续努力的一部分,本研究汇编并讨论了一个包含10个值得注意的张力、权衡及底层维度之间其他相互作用的目录。我们主要聚焦双边相互作用,并借鉴分散于多样化文献中的支持证据。该目录有助于提高人们对伦理原则各维度之间可能存在的相互作用的认识,并促进AI/ML系统的设计者和开发者作出有充分依据的判断。

英文摘要:

Many sets of ethics principles for responsible AI have been proposed to allay concerns about misuse and abuse of AI/ML systems. The underlying aspects of such sets of principles include privacy, accuracy, fairness, robustness, explainability, and transparency. However, there are potential tensions between these aspects that pose difficulties for AI/ML developers seeking to follow these principles. For example, increasing the accuracy of an AI/ML system may reduce its explainability. As part of the ongoing effort to operationalise the principles into practice, in this work we compile and discuss a catalogue of 10 notable tensions, trade-offs and other interactions between the underlying aspects. We primarily focus on two-sided interactions, drawing on support spread across a diverse literature. This catalogue can be helpful in raising awareness of the possible interactions between aspects of ethics principles, as well as facilitating well-supported judgements by the designers and developers of AI/ML 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。

↑