Perception-Aware Attack: Creating Adversarial Music via Reverse-Engineering Human Perception. (arXiv:2207.13192v1 [cs.SD])

Recently, adversarial machine learning attacks have posed serious security
threats against practical audio signal classification systems, including speech
recognition, speaker recognition, and music copyright detection. Previous
studies have mainly focused on ensuring the effectiveness of attacking an audio
signal classifier via creating a small noise-like perturbation on the original
signal. It is still unclear if an attacker is able to create audio signal
perturbations that can be well perceived by human beings in addition to its
attack effectiveness. This is …

adversarial attack engineering human music reverse