CVE Tools

CVE-2026-34760

vLLM: Downmix Implementation Differences as Attack Vectors Against Audio AI Models

Published: Apr 2, 2026Updated: May 11, 2026 Sources: CVE List NVDCWE-20

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.

No summary for this CVE yet.

CVSS Vector Breakdown

AV:NAC:HPR:LUI:NS:UC:NI:HA:L
Exploitability
AV:NAttack Vector
Network
AC:HAttack Complexity
High
PR:LPrivileges Required
Low
UI:NUser Interaction
None
Scope
S:UScope
Unchanged
Impact
C:NConfidentiality
None
I:HIntegrity
High
A:LAvailability
Low

Weaknesses

Affected Products

vllm-projectoss-projectAI / MLaka vllm, vllm-project/vllm
vllmoss-projectAI / MLaka aibrix

Exploitability

Official Patch Available

Attack Graph

Products CVE Techniques Tactics

Click technique nodes to view MITRE ATT&CK details. Scroll to zoom, drag to pan.

MITRE ATT&CK

1 technique
Initial Access
View detailed technique mapping

References

and 1 more references View all →

Timeline

Published
Apr 2, 2026
Last Updated
May 11, 2026

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
Plain-language analysis
Impact assessment and exploitation scenario in plain English
Attack graph visualization
Interactive attack path and kill chain mapping
Exploit details & PoC links
ExploitDB, Metasploit, GitHub PoCs with direct links
Nuclei scanner templates
Ready-to-use vulnerability scanner templates
Full remediation guide
Patch instructions, workarounds, and compliance impact
Interactive AI chat
Ask questions about this vulnerability in natural language
Related vulnerabilities
Semantically similar CVEs and attack patterns
REST API & MCP access
Integrate vulnerability data into your workflows