cs.AI, cs.CL, cs.CR, cs.LG, cs.SD

Sparse Tokens Suffice: Jailbreaking Audio Language Models via Token-Aware Gradient Optimization

arXiv:2605.04700v1 Announce Type: cross
Abstract: Jailbreak attacks on audio language models (ALMs) optimize audio perturbations to elicit unsafe generations, and they typically update the entire waveform densely throughout optimization. In this work,…