All vulnerabilities

Servers and applications

CVE-2026-34760

Downmix Implementation Differences as Attack Vectors Against Audio AI Models

Severity
High 7.1
Published
30 Mar 2026
Last changed
24 Jul 2026
Added to UpHeron
3 Nov 2026
Fixed in
0.18.0
Exploit chance
0.3% in the next 30 daysHigher than 21% of CVEs. EPSS by FIRST, 19 Nov 2026
Weakness
Improper input validation (CWE-20)
Attack
Over the network · Needs a user account · No user action needed
Attacker can
Change data · Slow it down
CVSS vector
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:H/A:L
Also known as
GHSA-6c4r-fmh3-7rh8
Sources
NVD, Project advisories (GitHub)

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.

From NVD.

Affected software

SoftwareAffected versions
vLLMServers and applications · cpe:a:vllm:vllm
  • From 0.5.5 before 0.18.0
vLLMServers and applications · github:vllm-project/vllm
  • From 0.5.5 before 0.18.0

About vLLM

open-source software for large language model inference

From Wikidata, CC0 1.0.
Docker Hub pulls
44,195,225Docker Hub, 15 Nov 2026
GitHub stars
96,943GitHub, 15 Nov 2026
Forks
24,836GitHub, 15 Nov 2026
Latest release
v0.33.0rc3GitHub, 15 Nov 2026
Released
2 Nov 2026GitHub
License
Apache Software License 2.0Wikidata
First published on GitHub
9 Feb 2023GitHub

References

  • NVD https://nvd.nist.gov/vuln/detail/CVE-2026-34760
  • CVE.org https://www.cve.org/CVERecord?id=CVE-2026-34760
  • GitHub Advisory Database https://github.com/advisories/GHSA-6c4r-fmh3-7rh8
  • github.com https://github.com/vllm-project/vllm/security/advisories/GHSA-6c4r-fmh3-7rh8