llamaCVEVulnerability Intelligence
/
Advisory · GitHub · PyPI · vllm

GHSA-6C4R-FMH3-7RH8

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

Parche disponible
Descargar PNG JSON
CVSS
—
medium
Fuente: —
ExplotaciónSin evidenciaNo figura en CISA KEV
Exploits públicos0Ninguno conocido
Parche1 versiónPrimer parche a -119 d de la divulgación
Exposición125 dDesde la divulgación, 17 jul 2026, 11:52 a. m.
Detección122 dDesde la divulgación hasta su ingreso al índice
Timeline

Ciclo de vida de la vulnerabilidad

Hoy
Divulgación
Publicada +1
Explotación
Remediación
Parche 0.18.0
Monitoreo
Detectada
20 mar 26
17 jul 26
17 nov 26
20 nov 26
20 mar 26
20 may 26
21 jul 26
20 sept 26
20 nov 26
FechaFaseEventoDetalle
Remediación Parche 0.18.0 vllm · -119 d desde divulgación
Divulgación Publicada GHSA-6C4R-FMH3-7RH8 divulgada
Divulgación Modificada Última actualización del registro
Monitoreo Detectada Ingresó al índice
Resumen
Descripción del advisory
Texto original · GitHub · en inglés

## Issue Description
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).

https://github.com/librosa/librosa/blob/af8c839fb15317fa2712ea66e7a22da6a9267b32/librosa/core/audio.py#L478
## Attack Scenario and Impact

### LFE (Low-Frequency Effects) Channel Exploit
Attackers can craft special multichannel audio files containing:
1. Normal content in front channels (L/R)
2. Either interference signals or hidden content in the LFE channel

Notice: It is worth noting that not only the LFE channel is excluded, but in fact, channels beyond the 6th (such as rear surround channels, overhead channels, height speakers, etc.) are also not supported.

Attack Methodology:

Attackers can create specially engineered multichannel audio with LFE interference, where front channels (L/R) contain normal content while the LFE channel carries interference signals or hidden content. When played on consumer devices that ignore LFE channels, only the normal content is heard. However, when processed by AI systems using Librosa (which mixes all channels), the LFE interference affects speech recognition feature extraction or masks critical detection features. This enables malicious content to bypass AI detection while still reaching end users, potentially compromising voice authentication systems, evading content moderation, or disrupting speech recognition accuracy.

Potential Exploitation Scenarios:
- Voice authentication systems may be tricked into accepting anomalous audio
- Content moderation systems may fail to detect prohibited content hidden in LFE channels
- Speech recognition systems may produce incorrect transcriptions

Note: `torch.audio` implements this correctly. Failure to do so may lead to inconsistencies between training and test audio, resulting in performance degradation.

Resources

  • ITU-R BS.775-4 Standard https://www.itu.int/dms_pubrec/itu-r/rec/bs/R-REC-BS.775-4-202212-I!!PDF-E.pdf
  • Librosa Source Code https://github.com/librosa/librosa/blob/af8c839fb15317fa2712ea66e7a22da6a9267b32/librosa/core/audio.py#L478
  • Librosa securty report https://github.com/librosa/librosa/security/advisories/GHSA-vfm7-86xr-5mrh

Fixes

  • https://github.com/vllm-project/vllm/pull/37058, which removes the librosa dependency from vLLM.

Incluye detalles técnicos publicados por el investigador. Úselos solo para validar y corregir sus propios sistemas.

Versiones

Rangos afectados

Afectada Corregida Última
vllm≥ 0.5.5 < 0.18.0
0.5.5
0.18.0
0.34.0
Remediación

Estado del parche por paquete

Paquete / productoEstadoCorregida enDesde divulgaciónÚltima versión
pypivllm
Corregida 0.18.0 -119 d 0.34.0 no afectada
Versiones corregidas0.18.0
Explotación

Arsenal público

Sin exploits, módulos ni PoC públicos conocidos a la fecha de verificación.

Referencias
Advisoryhttps://nvd.nist.gov/vuln/detail/CVE-2026-34760
Otrahttps://github.com/vllm-project/vllm/security/advisories/GHSA-6c4r-fmh3-7rh8
Otrahttps://github.com/vllm-project/vllm/pull/37058
Otrahttps://github.com/vllm-project/vllm/commit/c7f98b4d0a63b32ed939e2b6dfaa8a626e9b46c4
Otrahttps://github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2026-2299.yaml
Otrahttps://github.com/vllm-project/vllm
Otrahttps://github.com/vllm-project/vllm/releases/tag/v0.18.0

Las referencias externas se muestran para copiar: cve.llama.ec no lo redirige a otros sitios.