风险评测 · 技术报告

CAISI’s Assessment of Z.ai’s GLM-5.3 Cyber Capabilities | NIST

NUWA 研究解读 · 独立复核待完成

首次发表: 2026-09-17来源核验: 2026-10-25

原始来源 ↗引用本记录 ↓网络安全 →

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：综合落后时间依赖基准与能力激发，并非普适网络能力时钟。

研究问题

CAISI受控网络评测中GLM-5.3表现如何？

研究设计与假设

四个基准使用指定智能体预算与推理设置，并用1PL IRT估计带区间的综合指数。

来源发现

GLM-5.3在SEC-Bench Pro为74/183，40.4%，Wilson区间[33.6,47.7]。

ExploitGym为47/498，比较组分母502；ExploitBench为三次最佳分级进展。

NUWA 解读

NUWA 解读：综合落后时间依赖基准与能力激发，并非普适网络能力时钟。

局限与相反证据

每基准的前沿最佳可能不是同一模型，部分美国模型关闭防护。

研究与决策意义

模型建议：综合指数旁保留分母、不确定性与比较模型身份。

精确来源位置

CAISI’s Assessment of Z.ai’s GLM-5.3 Cyber Capabilities · Methodological NotesSelected original resource https://www.nist.gov/news-events/news/2026/09/caisis-assessment-zais-glm-53-cyber-capabilities; sha256:557d390e369fc6f22e708f779fff077c0a3cc41861bea018aa777701f758419f; archived source capture; exact capture time not independently established
CAISI’s Assessment of Z.ai’s GLM-5.3 Cyber Capabilities · Table 1 Cyber benchmark descriptionsSelected original resource https://www.nist.gov/news-events/news/2026/09/caisis-assessment-zais-glm-53-cyber-capabilities; sha256:557d390e369fc6f22e708f779fff077c0a3cc41861bea018aa777701f758419f; archived source capture; exact capture time not independently established
CAISI’s Assessment of Z.ai’s GLM-5.3 Cyber Capabilities · Table 2 Cyber benchmark resultsSelected original resource https://www.nist.gov/news-events/news/2026/09/caisis-assessment-zais-glm-53-cyber-capabilities; sha256:557d390e369fc6f22e708f779fff077c0a3cc41861bea018aa777701f758419f; archived source capture; exact capture time not independently established
CAISI’s Assessment of Z.ai’s GLM-5.3 Cyber Capabilities · Cyber capability index: 1PL IRT explanationSelected original resource https://www.nist.gov/news-events/news/2026/09/caisis-assessment-zais-glm-53-cyber-capabilities; sha256:557d390e369fc6f22e708f779fff077c0a3cc41861bea018aa777701f758419f; 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

发布机构美国 NIST／CAISI

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。

BibTeX ↓RIS ↓记录与来源元数据 · JSON ↓阅读覆盖 · JSON 提交更正

原始出版物 · BibTeX

@misc{caisi-glm-cyber-assessment,
  title = {CAISI’s Assessment of Z.ai’s GLM-5.3 Cyber Capabilities | NIST},
  url = {https://www.nist.gov/news-events/news/2026/09/caisis-assessment-zais-glm-53-cyber-capabilities},
  year = {2026},
  date = {2026-09-17},
  version = {Source capture 2026-10-25},
  note = {Source capture 2026-10-25}
}

NUWA 记录 · BibTeX

@misc{caisi-glm-cyber-assessment-nuwa,
  title = {CAISI’s Assessment of Z.ai’s GLM-5.3 Cyber Capabilities | NIST — NUWA research record},
  url = {https://whitzard.tech/nuwa/whitzard-index/work/caisi-glm-cyber-assessment/},
  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--caisi-glm-cyber-assessment.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--caisi-glm-cyber-assessment.json.}
}

证据快照 2026-10-29.1 · 索引更新 · RSS

参考文献

[1] CAISI’s Assessment of Z.ai’s GLM-5.3 Cyber Capabilities. 2026-09-17 ; Official publication masthead and article byline; Methodological Notes; Table 1 Cyber benchmark descriptions