Goto

Collaborating Authors

 cnn adversarial robustness


CNN Adversarial Robustness

#artificialintelligence

Below the great illustration from the paper "Towards deep learning models resistant to adversarial attacks" is shown. Here red stars are such pixel vicinities of training samples that after applying the initial separating hyperplane (here -- just black line) they occurred to lie in the region of the neighbor (so, wrong) class.