Advisory

GHSA-6c4r-fmh3-7rh8

Also known as: CVE-2026-34760, PYSEC-2026-2299

Summary

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

Details

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

Fixes

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

Severity

Medium Basis: The source's own band: MODERATE

Dates

Published
2026-07-17 16:52 UTC
Modified
2026-07-17 17:00 UTC

Affected packages and fixes

vllm

PyPI · All systems

Affected

  • introduced 0.5.5, fixed 0.18.0 (ecosystem)

Fixed versions

0.18.0

Fix

  • Fixed version 0.18.0
    pip install --upgrade vllm==0.18.0

Fix commands are the export's own generic commands. Ojuju never runs them. Check them against your setup first.

Check your own computer: guard packages check

View this record on OSV.dev

Source

Source: GitHub Advisory Database (reviewed advisories) · CC BY 4.0

Sources & licences