PyPI · vllm
vLLM: Processing differential in multi-channel audio downmixing enables hidden-input/moderation bypass for audio models
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:
Attackers can craft special multichannel audio files containing:
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:
Note: torch.audio implements this correctly. Failure to do so may lead to inconsistencies between training and test audio, resulting in performance degradation.
Is your project exposed to this? Stateward checks every dependency on every pull request and flags it only if your code actually reaches it.
Check my repoSources: CISA KEV (public domain), OSV.dev & GitHub Advisory Database (CC-BY-4.0), FIRST EPSS, NVD/CWE (public domain). Served live from the Stateward advisory database.