CVE-2026-34760
vLLM: Downmix Implementation Differences as Attack Vectors Against Audio AI 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.
CVSS Vector Breakdown
AV:NAttack VectorAC:HAttack ComplexityPR:LPrivileges RequiredUI:NUser InteractionS:UScopeC:NConfidentialityI:HIntegrityA:LAvailabilityWeaknesses
Affected Products
Exploitability
Attack Graph
Click technique nodes to view MITRE ATT&CK details. Scroll to zoom, drag to pan.
MITRE ATT&CK
1 techniqueReferences
Timeline
Unlock Complete Vulnerability Intelligence
Get the full picture for CVE-2026-34760 and every CVE in our database. Create a free account — no credit card required.
Create Free Account