发表机构
University of Pavia; University of Cantabria; Aristotle University of Thessaloniki（帕维亚大学; 坎塔布里亚大学; 亚里士多德大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出用多维洛伦兹区域体和基尼指数建模AI危害数据，以考虑严重性和多维性，并在MIT真实事件库上验证，发现环境等五类危害集中度最高，为干预优先级提供依据。
AI 中文摘要
虽然AI系统日益影响高风险社会领域，但其治理受限于缺乏基于实际危害的风险管理方法，这些方法需考虑危害的严重性而不仅仅是其可能性。因此，AI风险管理模型仍以合规驱动和提供者为中心，对危害如何危险以及干预优先级应如何确定提供的洞察有限。这一问题因危害数据通常是有序且多维的性质而加剧。为解决该问题并提供有效的风险评估方法，本文提出利用洛伦兹区域体（Lorenz Zonoids）和基尼指数（Gini indices）对危害数据进行建模。为此，我们建议将其扩展到多维设置，并展示如何为麻省理工学院提供的真实AI事件数据存储库实际计算这些指标。实证结果表明，环境、基础设施、财产、人身和民主相关危害在两个多维基尼指数下达到最高值，因此在其联合的直接、间接和推断的严重性-频率分布中表现出最强的集中性。这些集中模式可能有助于在确定缓解优先级时识别需要更密切审查的类别。
英文摘要
While AI systems increasingly shape high-stakes societal domains, their governance is limited by the lack of risk management methods that operate on real harms, taking their severity, and not only their likelihood, into account. As a consequence, AI risk management models remain compliance-driven and provider-centric, offering limited insight into how harms are dangerous, and on what should be the priority of intervention. The problem is amplified by the nature of harm data which are typically ordinal and multidimensional. To solve the problem, and offer an effective risk assessment methodology, in this paper we propose to model harm data by means of Lorenz Zonoids and Gini indices. To this aim we propose to extend them in a multidimensional setting, and show how to practically calculate them for a real AI incident data repository, provided by the Massachusetts Institute of Technology. The empirical findings indicate that environmental, infrastructure, property, physical, and democracy-related harms attain the highest values under the two multidimensional Gini indices and therefore exhibit the strongest concentration in their joint direct, indirect, and inferred severity-frequency distributions. These concentration patterns may help identify categories that warrant closer examination when mitigation priorities are determined.
Comments26 pages, 6 figures
