Preprint2026
From Inaudible Inputs to Model Failures: Low-Frequency Safety Risks in LALMs
Yuanhe Zhang, Weiliu Wang, Jie Ren, et al.
Proposes ILL, an inaudible red teaming method using low-frequency waveforms to attack LALMs, and DRG, a defense that detects distribution shifts and requests reacquisition, reducing accuracy by up to 67 points.
0Aug 10, 2026Attention MechanismsAi Safety
arXiv