Decision-based Black-box Attack Against Vision Transformers via Patch-wise Adversarial Removal. (arXiv:2112.03492v2 [cs.CV] UPDATED)

Vision transformers (ViTs) have demonstrated impressive performance and
stronger adversarial robustness compared to Convolutional Neural Networks
(CNNs). On the one hand, ViTs' focus on global interaction between individual
patches reduces the local noise sensitivity of images. On the other hand, the
neglect of noise sensitivity differences between image regions by existing
decision-based attacks further compromises the efficiency of noise compression,
especially for ViTs. Therefore, validating the black-box adversarial robustness
of ViTs when the target model can only be queried still …

adversarial attack box decision patch transformers