{"schemaVersion":"nuwa-current-record-1","version":"2026-10-29.1","publication":"published","work":{"id":"deepmind-dangerous-capabilities","title":"Evaluating Frontier Models for Dangerous Capabilities","aliases":[],"authors":["Mary Phuong","Matthew Aitchison","Elliot Catt","Sarah Cogan","Alexandre Kaskasoli","Victoria Krakovna","David Lindner","Matthew Rahtz","Yannis Assael","Sarah Hodkinson","Heidi Howard","Tom Lieberum","Ramana Kumar","Maria Abi Raad","Albert Webson","Lewis Ho","Sharon Lin","Sebastian Farquhar","Marcus Hutter","Gregoire Deletang","Anian Ruoss","Seliem El-Sayed","Sasha Brown","Anca Dragan","Rohin Shah","Allan Dafoe","Toby Shevlane"],"primaryFunction":"evaluation","secondaryFunctions":[],"kind":"study","sourceId":"deepmind-dangerous-capabilities-publication","attributionSourceId":"deepmind-dangerous-capabilities-publication-author-source","originalUrl":"https://arxiv.org/abs/2403.13793","publicationDate":"2024-03-20","updatedOn":"2026-10-25","areas":["autonomy","deception","cybersecurity"],"scopeNote":{"en":"Relevance is assigned to the research question and stated conditions of the work. A topic tag is not a risk rating.","zh":"风险关联依据研究问题及明确条件建立，主题标签不代表风险评级。"},"protocolIds":[],"contributions":[{"organizationId":"deepmind","role":"research","sourceId":"deepmind-capability-author-source","locator":"Official research publication and author list"}],"summary":{"en":"Pilots dangerous-capability evaluations covering cyber tasks, self-proliferation, self-reasoning and persuasion.","zh":"试行危险能力评测，覆盖网络任务、自我扩散、自我推理和说服。"},"note":{"question":null,"method":null,"finding":null,"supports":null,"limits":null,"connections":null},"resources":[],"noteStatus":{"question":"limited","method":"limited","finding":"limited","supports":"limited","limits":"limited","connections":"limited"},"noteAvailability":{"en":"A substantive NUWA research note is not yet available. The repeated draft sections were removed pending review of the original methods, findings and limitations; use the original publication for the research account.","zh":"实质性的 NUWA 研究笔记尚未完成。重复草稿章节已移除，待核查原始方法、发现与限制；研究内容请以原始出版物为准。"},"noteSourceLocator":"No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence.","tags":[]},"reading":{"id":"deepmind-dangerous-capabilities","title":"Evaluating Frontier Models for Dangerous Capabilities","en":{"question":"What warning signs can a structured dangerous-capability evaluation program reveal?","design":"Gemini 1.0 pilots span persuasion/deception, cyber, self-proliferation and self-reasoning, with multiple tasks and elicitation approaches.","findings":["The authors found no strong dangerous capabilities in tested models, while identifying early warning signs.","Vulnerability-patch classification accuracy differed substantially between datasets (§5.2)."],"interpretation":"NUWA interpretation: bounded negative findings depend on both task coverage and elicitation.","limits":"The program is an early pilot on specific model generations, not an enduring guarantee against future dangerous capabilities.","decisionRelevance":"Model recommendation: use the domain/task decomposition as an audit design reference and date every capability claim.","takeaway":"NUWA interpretation: bounded negative findings depend on both task coverage and elicitation.","connections":[],"scoring":null,"conditions":null,"statistics":"Vulnerability-patch classification accuracy differed substantially between datasets (§5.2).","usage":"Model recommendation: use the domain/task decomposition as an audit design reference and date every capability claim."},"zh":{"question":"系统性危险能力评测计划能发现哪些预警信号？","design":"Gemini 1.0试点评测说服欺骗、网络、自我扩散与自我推理，采用多任务和激发方式。","findings":["作者在受测模型未发现强危险能力，但指出早期信号。","漏洞补丁分类正确率在不同数据集明显不同（§5.2）。"],"interpretation":"NUWA 解读：有边界的阴性结果依赖任务覆盖与能力激发。","limits":"这是特定代际的早期试点，不是未来危险能力的持续保证。","decisionRelevance":"模型建议：把领域任务分解用于审计设计，并为所有能力结论标注时间。","takeaway":"NUWA 解读：有边界的阴性结果依赖任务覆盖与能力激发。","connections":[],"scoring":null,"conditions":null,"statistics":"漏洞补丁分类正确率在不同数据集明显不同（§5.2）。","usage":"模型建议：把领域任务分解用于审计设计，并为所有能力结论标注时间。"},"assertionPolicy":{"question":"source-research-question","design":"source-finding","findings":"source-finding","interpretation":"nuwa-interpretation","limits":"source-limit-or-explicit-editorial-scope-limit","connections":"source-supported-relationship-only","decisionRelevance":"model-recommendation-not-source-conclusion"},"sourceRefs":[{"sourceId":"deepmind-dangerous-capabilities-publication-author-source","url":"https://arxiv.org/html/2403.13793","locator":"Abstract","version":"Selected original resource https://arxiv.org/html/2403.13793; sha256:12872dcaaa7ad2297665fd85c8404512e050c28e5616ce15c854f536ea0fd945; archived source capture; exact capture time not independently established","artifactSha256":"12872dcaaa7ad2297665fd85c8404512e050c28e5616ce15c854f536ea0fd945"},{"sourceId":"deepmind-dangerous-capabilities-publication-author-source","url":"https://arxiv.org/html/2403.13793","locator":"§2 Overview of evaluations and agents","version":"Selected original resource https://arxiv.org/html/2403.13793; sha256:12872dcaaa7ad2297665fd85c8404512e050c28e5616ce15c854f536ea0fd945; archived source capture; exact capture time not independently established","artifactSha256":"12872dcaaa7ad2297665fd85c8404512e050c28e5616ce15c854f536ea0fd945"},{"sourceId":"deepmind-dangerous-capabilities-publication-author-source","url":"https://arxiv.org/html/2403.13793","locator":"§5.2 Results","version":"Selected original resource https://arxiv.org/html/2403.13793; sha256:12872dcaaa7ad2297665fd85c8404512e050c28e5616ce15c854f536ea0fd945; archived source capture; exact capture time not independently established","artifactSha256":"12872dcaaa7ad2297665fd85c8404512e050c28e5616ce15c854f536ea0fd945"},{"sourceId":"deepmind-dangerous-capabilities-publication-author-source","url":"https://arxiv.org/html/2403.13793","locator":"§6.4 Discussion","version":"Selected original resource https://arxiv.org/html/2403.13793; sha256:12872dcaaa7ad2297665fd85c8404512e050c28e5616ce15c854f536ea0fd945; archived source capture; exact capture time not independently established","artifactSha256":"12872dcaaa7ad2297665fd85c8404512e050c28e5616ce15c854f536ea0fd945"}],"publication":{"state":"published","publishedOn":"2026-10-29","authorizationReference":"user-authorized-global-index-publication-2026-10-29","reviewedCandidateId":"local-6efe31bc4a0c0f37"},"review":{"state":"published-note","sourceScope":"full-text","availableScope":null,"readingCoverage":"selected-source-sections; not a complete section-by-section paper audit","completePaperAudit":false,"independentEvidenceReview":"pending-human-review","bilingualEditorialReview":"pending-human-review","authorship":"model-assisted-research-note","preparedFingerprint":"1ba45f737cbee9f2951a063369abb6cdd4468383d2e4c2e5c03e6482e11d2f18"}},"sources":[{"id":"deepmind-dangerous-capabilities-publication","title":"Evaluating Frontier Models for Dangerous Capabilities","url":"https://arxiv.org/abs/2403.13793","version":"arXiv:2403.13793v2","publicationDate":"2024-03-20","datePrecision":"day","type":"paper","verifiedOn":"2026-10-25","documentId":"arxiv:2403.13793","authors":["Mary Phuong","Matthew Aitchison","Elliot Catt","Sarah Cogan","Alexandre Kaskasoli","Victoria Krakovna","David Lindner","Matthew Rahtz","Yannis Assael","Sarah Hodkinson","Heidi Howard","Tom Lieberum","Ramana Kumar","Maria Abi Raad","Albert Webson","Lewis Ho","Sharon Lin","Sebastian Farquhar","Marcus Hutter","Grégoire Delétang","Anian Ruoss","Seliem El-Sayed","Sasha Brown","Anca Dragan","Rohin Shah","Allan Dafoe","Toby Shevlane"],"aliases":["https://doi.org/10.48550/arXiv.2403.13793","https://arxiv.org/abs/2403.13793","https://arxiv.org/pdf/2403.13793"]}]}