Optimizing One-pixel Black-box Adversarial Attacks. (arXiv:2205.02116v1 [cs.CR])

The output of Deep Neural Networks (DNN) can be altered by a small
perturbation of the input in a black box setting by making multiple calls to
the DNN. However, the high computation and time required makes the existing
approaches unusable. This work seeks to improve the One-pixel (few-pixel)
black-box adversarial attacks to reduce the number of calls to the network
under attack. The One-pixel attack uses a non-gradient optimization algorithm
to find pixel-level perturbations under the constraint of a …

adversarial attacks box pixel