CVE-2026-34760
- Source
- https://cve.org/CVERecord?id=CVE-2026-34760
- Import Source
- https://storage.googleapis.com/cve-osv-conversion/osv-output/CVE-2026-34760.json
- JSON Data
- https://api.osv.dev/v1/vulns/CVE-2026-34760
- Aliases
- Published
- 2026-04-02T18:59:49Z
- Modified
- 2026-10-28T02:30:25Z
- Severity
-
- 5.9 (Medium) CVSS_V3 - CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:N/I:H/A:L CVSS Calculator
- Summary
- vLLM: Downmix Implementation Differences as Attack Vectors Against Audio AI Models
- Details
-
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.
- Database specific
{ "cna_assigner": "GitHub_M", "cwe_ids": [ "CWE-20" ], "osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/34xxx/CVE-2026-34760.json" }- References
-
- https://github.com/vllm-project/vllm/releases/tag/v0.18.0
- https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/34xxx/CVE-2026-34760.json
- https://github.com/vllm-project/vllm/security/advisories/GHSA-6c4r-fmh3-7rh8
- https://nvd.nist.gov/vuln/detail/CVE-2026-34760
- https://github.com/vllm-project/vllm/commit/c7f98b4d0a63b32ed939e2b6dfaa8a626e9b46c4
- https://github.com/vllm-project/vllm/pull/37058
Affected packages
Git / github.com/vllm-project/vllm
Affected ranges
- Type
- GIT
- Repo
- https://github.com/vllm-project/vllm
- Events
- Database specific
-
Show details
{ "extracted_events": [ { "cpe": "cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*", "range": [ { "introduced": "0.5.5" }, { "fixed": "0.18.0" } ], "source": "CPE_RANGE" }, { "range": [ { "fixed": "c7f98b4d0a63b32ed939e2b6dfaa8a626e9b46c4" } ], "source": "REFERENCES_COMMIT" }, { "original_tag": "v0.18.0", "range": [ { "fixed": "bcf2be96120005e9aea171927f85055a6a5c0cf6" } ], "source": "REFERENCES_TAG" } ] }
Affected versions
v0.*
v0.10.0
v0.10.0rc1
v0.10.0rc2
v0.10.1rc1
v0.10.2rc1
v0.10.2rc2
v0.11.0rc1
v0.11.1
v0.11.1rc0
v0.11.1rc1
v0.11.1rc2
v0.11.1rc3
v0.11.1rc4
v0.11.1rc5
v0.11.1rc6
v0.13.0rc1
v0.14.0rc0
v0.14.0rc1
v0.15.0rc1
v0.15.2rc0
v0.16.0rc0
v0.16.0rc1
v0.17.0rc0
v0.17.1rc0
v0.17.2rc0
v0.18.0rc0
v0.18.0rc1
v0.18.0rc2
v0.5.5
v0.6.0
v0.6.1
v0.6.1.post1
v0.6.1.post2
v0.6.2
v0.6.3
v0.6.3.post1
v0.6.4
v0.6.4.post1
v0.6.5
v0.6.6
v0.6.6.post1
v0.7.0
v0.7.1
v0.7.2
v0.7.3
v0.8.0rc1
v0.8.0rc2
v0.8.1
v0.8.2
v0.8.3rc1
v0.8.4
v0.9.0
v0.9.1
v0.9.1rc1
v0.9.1rc2
v0.9.2rc1