{"dataType":"CVE_RECORD","dataVersion":"5.2","cveMetadata":{"cveId":"CVE-2026-34760","assignerOrgId":"a0819718-46f1-4df5-94e2-005712e83aaa","state":"PUBLISHED","assignerShortName":"GitHub_M","dateReserved":"2026-03-30T19:17:10.225Z","datePublished":"2026-04-02T18:59:49.638Z","dateUpdated":"2026-04-03T14:42:34.842Z"},"containers":{"cna":{"title":"vLLM: Downmix Implementation Differences as Attack Vectors Against Audio AI Models","problemTypes":[{"descriptions":[{"cweId":"CWE-20","lang":"en","description":"CWE-20: Improper Input Validation","type":"CWE"}]}],"metrics":[{"cvssV3_1":{"attackComplexity":"HIGH","attackVector":"NETWORK","availabilityImpact":"LOW","baseScore":5.9,"baseSeverity":"MEDIUM","confidentialityImpact":"NONE","integrityImpact":"HIGH","privilegesRequired":"LOW","scope":"UNCHANGED","userInteraction":"NONE","vectorString":"CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:N/I:H/A:L","version":"3.1"}}],"references":[{"name":"https://github.com/vllm-project/vllm/security/advisories/GHSA-6c4r-fmh3-7rh8","tags":["x_refsource_CONFIRM"],"url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-6c4r-fmh3-7rh8"},{"name":"https://github.com/vllm-project/vllm/pull/37058","tags":["x_refsource_MISC"],"url":"https://github.com/vllm-project/vllm/pull/37058"},{"name":"https://github.com/vllm-project/vllm/commit/c7f98b4d0a63b32ed939e2b6dfaa8a626e9b46c4","tags":["x_refsource_MISC"],"url":"https://github.com/vllm-project/vllm/commit/c7f98b4d0a63b32ed939e2b6dfaa8a626e9b46c4"},{"name":"https://github.com/vllm-project/vllm/releases/tag/v0.18.0","tags":["x_refsource_MISC"],"url":"https://github.com/vllm-project/vllm/releases/tag/v0.18.0"}],"affected":[{"vendor":"vllm-project","product":"vllm","versions":[{"version":">= 0.5.5, < 0.18.0","status":"affected"}]}],"providerMetadata":{"orgId":"a0819718-46f1-4df5-94e2-005712e83aaa","shortName":"GitHub_M","dateUpdated":"2026-04-02T18:59:49.638Z"},"descriptions":[{"lang":"en","value":"vLLM is an inference and serving engine for large language models (LLMs). From version 0.5.5 to before version 0.18.0, Librosa defaults to using numpy.mean for mono downmixing (to_mono), while the international standard ITU-R BS.775-4 specifies a weighted downmixing algorithm. This discrepancy results in inconsistency between audio heard by humans (e.g., through headphones/regular speakers) and audio processed by AI models (Which infra via Librosa, such as vllm, transformer). This issue has been patched in version 0.18.0."}],"source":{"advisory":"GHSA-6c4r-fmh3-7rh8","discovery":"UNKNOWN"}},"adp":[{"metrics":[{"other":{"type":"ssvc","content":{"timestamp":"2026-04-03T14:42:25.211772Z","id":"CVE-2026-34760","options":[{"Exploitation":"none"},{"Automatable":"no"},{"Technical Impact":"partial"}],"role":"CISA Coordinator","version":"2.0.3"}}}],"title":"CISA ADP Vulnrichment","providerMetadata":{"orgId":"134c704f-9b21-4f2e-91b3-4a467353bcc0","shortName":"CISA-ADP","dateUpdated":"2026-04-03T14:42:34.842Z"}}]}}