NUWA 风险评测 · 评测基准
Evaluating Frontier Models for Stealth and Situational Awareness
NUWA 研究解读 · 独立复核待完成
NUWA Research Note
研究问题研究设计与假设来源发现NUWA 解读局限与相反证据研究与决策意义机构与角色原始资源模型辅助整理 · 选读原始全文或官方文章中的相关章节；尚未完成逐章节审计。
研究速读
NUWA 解读：这是安全论证内的条件性证据，不是全局安全认证。
研究问题
低隐蔽能力或情境推理能否支持有边界的谋划无能力论证？
研究设计与假设
五项隐蔽、十一项情境意识挑战采用分类通过规则，服务于一个明确安全论证。
来源发现
受测模型均未达到作者设定的关注阈值。
所提论证要求至少一类通过不足80%；论证不成立不等于已证明能谋划（§3.3）。
NUWA 解读
NUWA 解读：这是安全论证内的条件性证据，不是全局安全认证。
局限与相反证据
作者未专门防止能力隐藏；充分激发能力及公平人类比较是关键假设。
研究与决策意义
模型建议：将低分用于无能力证据前，先审查反驳条件与能力激发。
精确来源位置
- Evaluating Frontier Models for Stealth and Situational Awareness · AbstractSelected original resource https://arxiv.org/html/2505.01420v4; sha256:3d6d7f0188fb16f02f90d31a429b996cda133327c9a6f100efd3616f73b19315; archived source capture; exact capture time not independently established
- Evaluating Frontier Models for Stealth and Situational Awareness · §2.3 Possible defeatersSelected original resource https://arxiv.org/html/2505.01420v4; sha256:3d6d7f0188fb16f02f90d31a429b996cda133327c9a6f100efd3616f73b19315; archived source capture; exact capture time not independently established
- Evaluating Frontier Models for Stealth and Situational Awareness · §3.3 Evaluation thresholds for the safety caseSelected original resource https://arxiv.org/html/2505.01420v4; sha256:3d6d7f0188fb16f02f90d31a429b996cda133327c9a6f100efd3616f73b19315; archived source capture; exact capture time not independently established
- Evaluating Frontier Models for Stealth and Situational Awareness · §7.2 LimitationsSelected original resource https://arxiv.org/html/2505.01420v4; sha256:3d6d7f0188fb16f02f90d31a429b996cda133327c9a6f100efd3616f73b19315; archived source capture; exact capture time not independently established
来源核查、数据提取、编辑批准与实验复现分别记录。 方法说明 →
机构与角色
作者 (9)
Mary Phuong · Roland S. Zimmermann · Ziyue Wang · David Lindner · Victoria Krakovna · Sarah Cogan · Allan Dafoe · Lewis Ho · Rohin Shah
评测协议
引用与复用
引用研究发现时请引用原始出版物；引用 NUWA 的整理与解释时，单独引用本站记录及对应快照。
原始出版物 · BibTeX
@misc{stealth-evals,
title = {Evaluating Frontier Models for Stealth and Situational Awareness},
url = {https://arxiv.org/abs/2505.01420v4},
author = {Mary Phuong and Roland S. Zimmermann and Ziyue Wang and David Lindner and Victoria Krakovna and Sarah Cogan and Allan Dafoe and Lewis Ho and Rohin Shah},
year = {2025},
date = {2025-05-02},
version = {arXiv:2505.01420v4},
note = {arXiv:2505.01420v4}
}
NUWA 记录 · BibTeX
@misc{stealth-evals-nuwa,
title = {Evaluating Frontier Models for Stealth and Situational Awareness — NUWA research record},
url = {https://whitzard.tech/nuwa/whitzard-index/work/stealth-evals/},
version = {2026-10-29.1},
organization = {NUWA Frontier AI Safety Lab},
howpublished = {Retained note edition: https://whitzard.tech/nuwa/whitzard-index/data/record-editions/2026-10-29.1--stealth-evals.json},
note = {NUWA research note. Source-reading scope and independent review status are stated on the record. Snapshot 2026-10-29.1. Retained note edition: https://whitzard.tech/nuwa/whitzard-index/data/record-editions/2026-10-29.1--stealth-evals.json.}
}
证据快照 2026-10-29.1 · 索引更新 · RSS
参考文献
- [1] Mary Phuong, Roland S. Zimmermann 等. Evaluating Frontier Models for Stealth and Situational Awareness. 2025-07-03. v4 [arXiv]; Author affiliations on the original paper title page; Abstract; §2.3 Possible defeaters