Логотип exploitDog
Консоль
Логотип exploitDog

exploitDog

nvd логотип

CVE-2026-34760

Опубликовано: 02 апр. 2026
Источник: nvd
CVSS3: 5.9
CVSS3: 7.1
EPSS Низкий

Описание

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.

Уязвимые конфигурации

Конфигурация 1
cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*
Версия от 0.5.5 (включая) до 0.18.0 (исключая)

EPSS

Процентиль: 19%
0.00267
Низкий

5.9 Medium

CVSS3

7.1 High

CVSS3

Дефекты

CWE-20

Связанные уязвимости

CVSS3: 5.9
redhat
4 месяца назад

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.

CVSS3: 5.9
debian
4 месяца назад

vLLM is an inference and serving engine for large language models (LLM ...

CVSS3: 5.9
github
25 дней назад

vLLM: Processing differential in multi-channel audio downmixing enables hidden-input/moderation bypass for audio models

EPSS

Процентиль: 19%
0.00267
Низкий

5.9 Medium

CVSS3

7.1 High

CVSS3

Дефекты

CWE-20