AI 中文总结
提出 Eticas AI 风险分类法 v2.0.0，通过端到端示例（PII 泄露）展示从风险概念到可操作测试、测量和评级的完整桥梁，并开放分类法框架。
AI 中文摘要
AI 系统在高风险领域的快速部署产生了对标准化评估的迫切需求，然而该领域仍因相互竞争的风险分类法而碎片化，这些分类法仅编录风险，未展示审计如何执行。目前至少有 74 种 AI 风险分类法，几乎都止步于编录。审计的难点不在于命名风险，而在于操作化：将其转化为针对真实系统的测试运行、测量值、校准严重性和可辩护的评级。本文搭建了这一桥梁。我们展示了 Eticas 构建并运行的操作化层，以单一风险（PII 泄露）对公共基准进行端到端演示，然后介绍了使该方法可扩展的开放分类法。在 GPT-4-0314 上，随着对抗性条件增强，七个外部框架要求控制的披露风险测量为 0%、51% 和 84% 的披露率，通过校准的严重性带映射到子类别评级 E（SYSTEMIC 模式）。围绕此示例，Eticas AI 风险分类法 v2.0.0 组织了 10 个类别和 20 个子组下的 76 个活跃子类别，并映射到 18 个外部框架（涵盖合规、参考和学术层级）。其类别和子组层以 CC BY 4.0 发布为开放语义基础设施，具有稳定 URI 和 SKOS/JSON-LD 分发，一个完整的子类别示例展示了操作层直至其严重性阈值。贡献在于展示了从概念到分级发现的桥梁，以风险与其显现机制的清晰分离为基础，并以开放核心模型为框架，其中概念骨架开放，方法校准为实践者层。这是 AI 审计领域所需的基础设施：共享、开放且可证明可操作。
英文摘要
The rapid deployment of AI systems across high-stakes domains has created urgent demand for standardized evaluation, yet the field remains fragmented across competing risk taxonomies that catalog risks without showing how an audit is executed. At least 74 AI risk taxonomies exist, and almost all stop at the catalog. The hard part of auditing is not naming a risk but operationalizing it: turning it into a test run against a real system, a measured value, a calibrated severity, and a defensible grade. This paper leads with that bridge. We present the operationalization layer Eticas has built and run, shown end to end on a single risk (PII leakage) against a public benchmark, and then the open taxonomy that makes the method scale. On GPT-4-0314, a disclosure risk that seven external frameworks require be controlled is measured at 0%, 51%, and 84% disclosure as adversarial conditioning increases, mapping through calibrated severity bands to a subcategory grade of E with a SYSTEMIC pattern. Around this example, the Eticas AI Risk Taxonomy v3.0.0 organizes 70 active subcategories across 10 categories and 21 sub-groups, with mappings to 18 external frameworks across compliance, reference, and academic tiers. Its established layer - categories, sub-groups, and the 32 established subcategories - is published under CC BY 4.0 as open semantic infrastructure with stable URIs and SKOS/JSON-LD distributions, and a worked subcategory example shows the operational layer down to its severity thresholds. The contribution is the demonstrated bridge from concept to graded finding, anchored by a clean separation of risks from the mechanisms by which they surface, and framed by an open-core model in which the conceptual scaffold is open and the methodology calibration is the practitioner layer. This is the infrastructure the AI auditing field needs: shared, open, and demonstrably operable.
