4 matches found
vLLM: Processing differential in multi-channel audio downmixing enables hidden-input/moderation bypass for audio models
Issue Description Librosa defaults to using numpy.mean for mono downmixing tomono, 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...
CVE-2026-34760 vLLM: Downmix Implementation Differences as Attack Vectors Against Audio AI Models
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 tomono, while the international standard ITU-R BS.775-4 specifies a weighted downmixing algorithm. This discrepancy results...
CVE-2026-34760 vLLM: Downmix Implementation Differences as Attack Vectors Against Audio AI Models
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 tomono, while the international standard ITU-R BS.775-4 specifies a weighted downmixing algorithm. This discrepancy results...
CVE-2026-34760 vLLM: Downmix Implementation Differences as Attack Vectors Against Audio AI Models
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 tomono, while the international standard ITU-R BS.775-4 specifies a weighted downmixing algorithm. This discrepancy results...