Attention-Guided Black-box Adversarial Attacks with Large-Scale Multiobjective Evolutionary Optimization. (arXiv:2101.07512v3 [cs.CV] UPDATED)

Fooling deep neural networks (DNNs) with the black-box optimization has
become a popular adversarial attack fashion, as the structural prior knowledge
of DNNs is always unknown. Nevertheless, recent black-box adversarial attacks
may struggle to balance their attack ability and visual quality of the
generated adversarial examples (AEs) in tackling high-resolution images. In
this paper, we propose an attention-guided black-box adversarial attack based
on the large-scale multiobjective evolutionary optimization, termed as LMOA. By
considering the spatial semantic information of images, we …

arxiv attacks attention cv optimization