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 2104.12582cs.CYcs.AI
收藏

理解与规避AI故障:实用指南

Understanding and Avoiding AI Failures: A Practical Guide

University of Louisville(路易斯维尔大学)

Heather M. Williams, Roman V. Yampolskiy

AI总结:

该研究结合多类系统理论构建AI应用风险理解框架,运用AI安全原则量化AI智能提升与类人特质的独特风险,明确当代AI系统的安全关注重点。

摘要:

随着AI技术能力提升且普及度提高,AI事故正变得愈发常见。基于正常事故理论、高可靠性理论和开放系统理论,我们构建了一个用于理解AI应用相关风险的框架。此外,我们还运用AI安全原则,对AI智能水平提升以及类人特质所带来的独特风险进行量化。这两个领域的结合,更全面地呈现了当代AI的风险全貌。通过聚焦事故临近时的系统特性而非探寻事故的根本原因,我们明确了当前一代AI系统需要关注安全的方向。

英文摘要:

As AI technologies increase in capability and ubiquity, AI accidents are becoming more common. Based on normal accident theory, high reliability theory, and open systems theory, we create a framework for understanding the risks associated with AI applications. In addition, we also use AI safety principles to quantify the unique risks of increased intelligence and human-like qualities in AI. Together, these two fields give a more complete picture of the risks of contemporary AI. By focusing on system properties near accidents instead of seeking a root cause of accidents, we identify where attention should be paid to safety for current generation 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。

↑