Towards Lightweight Black-Box Attacks against Deep Neural Networks. (arXiv:2209.14826v3 [cs.LG] UPDATED)

Black-box attacks can generate adversarial examples without accessing the
parameters of target model, largely exacerbating the threats of deployed deep
neural networks (DNNs). However, previous works state that black-box attacks
fail to mislead target models when their training data and outputs are
inaccessible. In this work, we argue that black-box attacks can pose practical
attacks in this extremely restrictive scenario where only several test samples
are available. Specifically, we find that attacking the shallow layers of DNNs
trained on a …

attacks box networks neural networks