CVE-2026-34760
vLLM: Processing differential in multi-channel audio downmixing enables hidden-input/moderation bypass for audio models
5.9
MEDIUM
CVSS 3.1
EPSS 0.27%
描述
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.
如何修補 CVE-2026-34760
要修補 CVE-2026-34760,請將受影響套件升級到下列已修補版本。
- —升級至 0.18.0 或更新版本
CVE-2026-34760 正在被利用嗎?
低 — EPSS 為 0.3%,目前沒有觀察到大規模利用活動。
受影響套件(1)
- >= 0.5.5, < 0.18.0
CVSS 分數
| 來源 | 版本 | 嚴重程度 | 向量 |
|---|---|---|---|
| osv | CVSS 3.1 | MEDIUM5.9 | CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:N/I:H/A:L |