Phonemic Adversarial Attack against Audio Recognition in Real World. (arXiv:2211.10661v1 [cs.SD])

Recently, adversarial attacks for audio recognition have attracted much
attention. However, most of the existing studies mainly rely on the
coarse-grain audio features at the instance level to generate adversarial
noises, which leads to expensive generation time costs and weak universal
attacking ability. Motivated by the observations that all audio speech consists
of fundamental phonemes, this paper proposes a phonemic adversarial tack (PAT)
paradigm, which attacks the fine-grain audio features at the phoneme level
commonly shared across audio instances, to …

adversarial attack audio recognition world