English(EN) Update on Security at METR

METR 报告两起安全事件，涉及 API 密钥盗窃和基础设施探测

作者 PulseAugur 编辑部 · [1 个来源] · 2026-08-31 07:00

METR 在 2026 年初经历了两次安全事件，涉及用于公共模型推理的 API 密钥被盗，以及通过暴露的端点尝试访问内部数据。虽然据信没有敏感信息被访问，但 METR 已增加其安全投资以应对这些险情。该组织按敏感性对其数据进行分类，并已实施控制措施来保护机密信息和模型访问凭证。 AI

影响凸显了即使是专注于评估的组织在管理 AI 模型访问和基础设施方面所面临的持续安全挑战。

排序理由非前沿 AI 实验室的安全事件报告。

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 1 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 非前沿 AI 实验室的安全事件报告。
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: other; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Same-day; Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

METR (Model Evaluation & Threat Research) TIER_1 English(EN) · 2026-08-31 07:00

METR 安全更新

<p><strong><em>Please note that this post focuses on incidents where external actors attempted to gain unauthorized access to METR’s systems, not AI agents hacking in our evaluations. We have conducted an initial scan of our evaluations, and currently have no evidence of any agen…