Vulnerability · Published Apr 2, 2026 · Assigned by GitHub_M
CVE-2026-34760vLLM: Downmix Implementation Differences as Attack Vectors Against Audio AI Models
Medium 5.9
In plain English
A medium-severity improper input validation in vllm from vllm-project. There are no confirmed reports of exploitation so far. The chance it is exploited in the next 30 days is estimated at 0.3% (higher than 20% of all known vulnerabilities). Fixed versions are available - upgrade the affected package.
Official description
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.
Affected packages & fixed versions
| Ecosystem | Package | Fixed in | Advisory |
|---|---|---|---|
| PyPI | vllm | 0.18.0 | GHSA-6c4r-fmh3-7rh8 |
| PyPI | vllm | 0.18.0 | PYSEC-2026-2299 |
Affected products (as reported)
| Vendor | Product | Versions |
|---|---|---|
| vllm-project | vllm | >= 0.5.5, < 0.18.0 |
Weakness: CWE-20 · Vector: CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:N/I:H/A:L
References
- https://github.com/vllm-project/vllm/security/advisories/GHSA-6c4r-fmh3-7rh8 x_refsource_CONFIRM
- https://github.com/vllm-project/vllm/pull/37058 x_refsource_MISC
- https://github.com/vllm-project/vllm/commit/c7f98b4d0a63b32ed939e2b6dfaa8a626e9b46c4 x_refsource_MISC
- https://github.com/vllm-project/vllm/releases/tag/v0.18.0 x_refsource_MISC