AIBearisharXiv – CS AI · 5h ago7/10
🧠
Hearing the Unspoken: Language Model Priors for Acoustic Adversarial Attacks
Researchers demonstrate a new adversarial attack called Semantic Gambit that exploits Large Language Models to significantly compromise real-time Automatic Speech Recognition systems. By leveraging predictive context from LLMs, the attack achieves a 35.6% Word Error Rate—three times higher than previously documented attacks—revealing a critical vulnerability in ASR pipelines that operate under temporal constraints.