CVE-2026-34760
vLLM: Processing differential in multi-channel audio downmixing enables hidden-input/moderation bypass for audio models
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.
How to fix CVE-2026-34760
To remediate CVE-2026-34760, upgrade the affected package to a fixed version below.
- —upgrade to 0.18.0 or later
Is CVE-2026-34760 being exploited?
Low — EPSS is 0.3%, meaning exploitation activity has not been observed at scale.
Affected packages (1)
- >= 0.5.5, < 0.18.0
CVSS scores
| Source | Version | Severity | Vector |
|---|---|---|---|
| osv | CVSS 3.1 | MEDIUM5.9 | CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:N/I:H/A:L |