Goal Reached Thanks to every supporter — we hit 100%!

Goal: 1000 CNY · Raised: 1359 CNY

100%
Buy Us a Coffee

CVE-2026-34760— vLLM: Downmix Implementation Differences as Attack Vectors Against Audio AI Models

Quick assessment

Affected
vllm-project vllm
Exploitation
No confirmed in-the-wild exploitation; assess based on exposure
Recommended action
Check the vendor advisory and references for a fixed version. If immediate upgrade is impossible, restrict exposure and increase monitoring.

vLLM是vLLM开源的一个适用于 LLM 的高吞吐量和内存高效推理和服务引擎。 vLLM 0.5.5至0.18.0之前版本存在输入验证错误漏洞，该漏洞源于音频单声道下混算法与国际标准不一致，可能导致AI模型处理的音频与人类听到的音频存在差异。

CVSS 5.9 · Medium EPSS 0.48% · P39

Possible ATT&CK Techniques 1 AI

T1555.004 · Windows Credential Manager
Get alerts for future matching vulnerabilities Log in to subscribe

I. Basic Information for CVE-2026-34760

Vulnerability Information
Have questions about the vulnerability? See if Shenlong's analysis helps!
View Shenlong Deep Dive ↗

Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.

Vulnerability Title
vLLM: Downmix Implementation Differences as Attack Vectors Against Audio AI Models
Source: CVE Program / CVE List V5
Vulnerability 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.
Source: CVE Program / CVE List V5
CVSS Information
CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:N/I:H/A:L
Source: CVE Program / CVE List V5
Vulnerability Type
输入验证不恰当
Source: CVE Program / CVE List V5
Vulnerability Title
vLLM 输入验证错误漏洞
Source: CNNVD (China National Vulnerability Database)
Vulnerability Description
vLLM是vLLM开源的一个适用于 LLM 的高吞吐量和内存高效推理和服务引擎。 vLLM 0.5.5至0.18.0之前版本存在输入验证错误漏洞，该漏洞源于音频单声道下混算法与国际标准不一致，可能导致AI模型处理的音频与人类听到的音频存在差异。
Source: CNNVD (China National Vulnerability Database)
CVSS Information
N/A
Source: CNNVD (China National Vulnerability Database)
Vulnerability Type
N/A
Source: CNNVD (China National Vulnerability Database)

Affected Products

Vendor Product Affected Versions CPE Subscribe
vllm-project vllm >= 0.5.5, < 0.18.0 -

II. Public POCs for CVE-2026-34760

# POC Description Source Link Shenlong Link
AI-Generated POC Premium

No public POC found.

Login to generate AI POC

III. Intelligence Information for CVE-2026-34760

请登录查看更多情报信息。

Patches & Fixes for CVE-2026-34760 (1)

Vendor Advisories for CVE-2026-34760 (1)

Vendor Pages for CVE-2026-34760 (1)

IV. Related Vulnerabilities

Same product: vllm
Same vendor: vllm-project
Same weakness: CWE-20

V. Comments for CVE-2026-34760

No comments yet

Leave a comment