arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2512.01166cs.CY
收藏

评估AI提供商的前沿安全框架

Evaluating AI Providers' Frontier Safety Frameworks

SaferAI

Lily Stelling, Malcolm Murray, Bruno Galizzi, Max Schaffelder, Siméon Campos, Henry Papadatos

阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文评估12家AI公司的前沿安全框架，通过65项加权标准评估四个维度，发现框架存在诸多缺失或不明确之处，评分范围从34%到8%，建议未来需完善以提升问责功能。

摘要：

在2024年AI首尔峰会之后，十二家AI公司发布了前沿AI安全框架，概述了管理高级AI系统灾难性风险的方法。新兴立法日益将这些框架视为外部问责机制，并将其纳入报告要求。但这些框架实际承诺了什么？本研究评估了12个框架，使用65项加权标准，涵盖风险识别、风险分析与评估、风险处理和风险治理四个维度。我们的标准借鉴了其他高风险行业（如航空、核能）已建立的风险管理原则，遵循Campos等人（2025）的方法。总体评分范围从34%（Anthropic）到8%（Cohere），中位数为18%。许多方面缺失或未明确说明。这些低分可能源于AI风险管理的初级阶段，相较于有数十年经验的行业。然而，当前框架作为问责功能有限，承诺模糊，难以预测公司决策、评估计划响应是否充分或确定承诺是否履行。尽管如此，当前约束下更高的评分似乎可行：一家采用所有领先实践的公司可得54分，是当前中位数的三倍。

英文摘要：

Following the AI Seoul Summit in 2024, twelve AI companies published frontier AI safety frameworks (Frameworks) outlining their approaches to managing catastrophic risks from advanced AI systems. Emerging legislation increasingly treats these Frameworks as external accountability mechanisms, incorporating them into reporting requirements. But what do the Frameworks actually commit each company to do? This study assesses 12 Frameworks, using 65 weighted criteria, across four dimensions: risk identification, risk analysis \& evaluation, risk treatment, and risk governance. Our criteria adapt established risk management principles from other high-risk industries (e.g. aviation, nuclear power) to the frontier AI context, following Campos et al. (2025). Overall scores range from 34% (Anthropic) to 8% (Cohere), with a median of 18%. Many aspects are missing or under-specified. These low scores may be natural given the nascency of AI risk management compared to industries with decades of practice. Nonetheless, current Frameworks are limited as accountability functions, with vague commitments that make it difficult to predict company decisions, assess whether planned responses are adequate, or determine whether commitments have been kept. Still, higher scores appear feasible within current constraints: a company adopting all leading practices currently adopted across their peers would score 54%, which is triple the current median.

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。

↑