Watch What You Pretrain For: Targeted, Transferable Adversarial Examples on Self-Supervised Speech Recognition models. (arXiv:2209.13523v1 [cs.LG])

Targeted adversarial attacks against Automatic Speech Recognition (ASR) are
thought to require white-box access to the targeted model to be effective,
which mitigates the threat that they pose. We show that the recent line of
Transformer ASR models pretrained with Self-Supervised Learning (SSL) are much
more at risk: adversarial examples generated against them are transferable,
making these models vulnerable to targeted, zero-knowledge attacks. We release
an adversarial dataset that partially fools most publicly released
SSL-pretrained ASR models (Wav2Vec2, HuBERT, WavLM, …

arxiv examples speech speech recognition speech recognition models