CVE-2026-34760
vLLM: Downmix Implementation Differences as Attack Vectors Against Audio AI Models
CVSS Score
5.9
EPSS Score
0.1%
EPSS Percentile
18th
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.
| CWE | CWE-20 |
| Vendor | vllm-project |
| Product | vllm |
| Published | Apr 2, 2026 |
| Last Updated | Apr 3, 2026 |
Stay Ahead of the Next One
Get instant alerts for vllm-project vllm
Be the first to know when new medium vulnerabilities affecting vllm-project vllm are published — delivered to Slack, Telegram or Discord.
Get Free Alerts →
Free · No credit card · 60 sec setup
CVSS v3 Breakdown
CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:N/I:H/A:L Attack Vector
Network
Attack Complexity
High
Privileges Required
Low
User Interaction
None
Scope
Unchanged
Confidentiality
None
Integrity
High
Availability
Low
Affected Versions
vllm-project / vllm
>= 0.5.5, < 0.18.0
References
github.com: https://github.com/vllm-project/vllm/security/advisories/GHSA-6c4r-fmh3-7rh8 github.com: https://github.com/vllm-project/vllm/pull/37058 github.com: https://github.com/vllm-project/vllm/commit/c7f98b4d0a63b32ed939e2b6dfaa8a626e9b46c4 github.com: https://github.com/vllm-project/vllm/releases/tag/v0.18.0