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...

TrojanPraise: Jailbreak LLMs Via Benign Fine-Tuning

The demand of customized large language models LLMs has led to commercial LLMs offering black-box fine-tuning APIs, yet this convenience introduces a critical security loophole: attackers could jailbreak the LLMs by fine-tuning them with malicious data. Though this security issue has recently bee...