{"schemaVersion":"nuwa-current-record-1","version":"2026-10-29.1","publication":"published","work":{"id":"cyberseceval","title":"CyberSecEval 4","aliases":["Meta CyberSecEval / CyberSecEval 4"],"authors":[],"primaryFunction":"evaluation","secondaryFunctions":[],"kind":"benchmark","sourceId":"cyberseceval-publication","attributionSourceId":"cyberseceval-publication","originalUrl":"https://meta-llama.github.io/PurpleLlama/CyberSecEval/docs/intro","publicationDate":null,"updatedOn":"2026-10-25","areas":["cybersecurity"],"scopeNote":{"en":"The main dimension follows the task outcome in the original protocol. Topic relevance is documented in the parent research record; no unreviewed question-level links are inferred.","zh":"主维度依据原协议的任务结果确定。主题关联见研究档案，不推断尚未审阅的问题级关联。"},"protocolIds":["cyberseceval"],"contributions":[{"organizationId":"meta","role":"publisher","sourceId":"cyberseceval-publication","locator":"Official publication masthead and article byline"}],"summary":{"en":"Provides evaluation suites for cyber capabilities and safeguards, with distinct task families and release-specific protocols.","zh":"提供网络能力与防护评测套件，分别组织任务族和版本协议。"},"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":"cyberseceval","title":"CyberSecEval 4","en":{"question":"What security constructs does the CyberSecEval suite cover?","design":"The version-four documentation separates offensive assistance, injection/interpreter risks and defensive tasks, adding CyberSOCEval and AutoPatchBench.","findings":["CyberSOCEval contributes malware-analysis and threat-intelligence reasoning tests.","AutoPatchBench evaluates repair of native-code security defects; the introduction provides no unified performance result."],"interpretation":"NUWA interpretation: this is a suite map, not one benchmark or one risk score.","limits":"The introductory documentation does not establish all component protocols, versions, sample counts or comparable scores.","decisionRelevance":"Model recommendation: select and cite the component-specific documentation before comparing models.","takeaway":"NUWA interpretation: this is a suite map, not one benchmark or one risk score.","connections":[],"scoring":null,"conditions":null,"statistics":null,"usage":"Model recommendation: select and cite the component-specific documentation before comparing models."},"zh":{"question":"CyberSecEval套件覆盖哪些安全构念？","design":"第四版文档区分攻击辅助、注入与解释器风险以及防御任务，并新增CyberSOCEval和AutoPatchBench。","findings":["CyberSOCEval含恶意软件分析与威胁情报推理。","AutoPatchBench测原生代码安全修补；介绍未给统一表现结果。"],"interpretation":"NUWA 解读：这是套件地图，不是单一基准或风险分数。","limits":"介绍不足以确立所有组件协议、版本、样本数或可比得分。","decisionRelevance":"模型建议：比较模型前选择并引用具体组件文档。","takeaway":"NUWA 解读：这是套件地图，不是单一基准或风险分数。","connections":[],"scoring":null,"conditions":null,"statistics":null,"usage":"模型建议：比较模型前选择并引用具体组件文档。"},"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":"cyberseceval-publication","url":"https://meta-llama.github.io/PurpleLlama/CyberSecEval/docs/intro","locator":"Introduction: CyberSecEval 4 overview","version":"Selected original resource https://meta-llama.github.io/PurpleLlama/CyberSecEval/docs/intro; sha256:d1fa0b20e03bb8672ef79d157f38f9167109068cfcf0ad7f12ada2abcc3457f7; archived source capture; exact capture time not independently established","artifactSha256":"d1fa0b20e03bb8672ef79d157f38f9167109068cfcf0ad7f12ada2abcc3457f7"},{"sourceId":"cyberseceval-publication","url":"https://meta-llama.github.io/PurpleLlama/CyberSecEval/docs/intro","locator":"Benchmark descriptions: CyberSOCEval and AutoPatch Tests","version":"Selected original resource https://meta-llama.github.io/PurpleLlama/CyberSecEval/docs/intro; sha256:d1fa0b20e03bb8672ef79d157f38f9167109068cfcf0ad7f12ada2abcc3457f7; archived source capture; exact capture time not independently established","artifactSha256":"d1fa0b20e03bb8672ef79d157f38f9167109068cfcf0ad7f12ada2abcc3457f7"}],"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":"1584349a788106d06e0ab355a7422936a2fd1996db50b5077c13c320e5b57eb9"}},"sources":[{"id":"cyberseceval-publication","title":"Introduction","url":"https://meta-llama.github.io/PurpleLlama/CyberSecEval/docs/intro","version":"Source capture 2026-10-25","publicationDate":null,"datePrecision":"unknown","type":"research-publication","verifiedOn":"2026-10-25","documentId":"https://meta-llama.github.io/PurpleLlama/CyberSecEval/docs/intro"}]}