A black-box adversarial attack strategy with adjustable sparsity and generalizability for deep image classifiers

作者：

Highlights：

• Presents a simple and efficient black-box adversarial attack strategy.

• The adversarial perturbation can be dense or sparse.

• Both universal and image dependent adversarial attack can be performed.

• Employs a simple variant of Differential Evolution capable of optimizing the high dimensional problem under concern.

摘要

•Presents a simple and efficient black-box adversarial attack strategy.•The adversarial perturbation can be dense or sparse.•Both universal and image dependent adversarial attack can be performed.•Employs a simple variant of Differential Evolution capable of optimizing the high dimensional problem under concern.

论文关键词：Adversarial attack,Black-box attack,Convolutional image classifier,Differential evolution,Sparse universal attack

论文评审过程：Received 25 November 2020, Revised 11 August 2021, Accepted 22 August 2021, Available online 24 August 2021, Version of Record 9 September 2021.

论文官网地址：https://doi.org/10.1016/j.patcog.2021.108279