CVE-2026-34760

Severity CVSS v4.0:

Pending analysis

Type:

CWE-20 Input Validation

Publication date:

02/04/2026

Last modified:

03/04/2026

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.

Impact

Vector 3.x

CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:N/I:H/A:L CVSS v3.1 Severity and Metrics:

Base Score: 5.90 MEDIUM
Vector: CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:N/I:H/A:L

Attack Vector (AV): Network
Attack Complexity (AC): High
Privileges Required (PR): Low
User Interaction (UI): None
Scope (S): Unchanged
Confidentiality (C): None
Integrity (I): High
Availability (A): Low

Base Score 3.x

5.90

Severity 3.x

MEDIUM

CVE-2026-34760

Description

Impact

References to Advisories, Solutions, and Tools