Universal Adversarial Directions. (arXiv:2210.15997v1 [cs.LG])

Despite their great success in image recognition tasks, deep neural networks
(DNNs) have been observed to be susceptible to universal adversarial
perturbations (UAPs) which perturb all input samples with a single perturbation
vector. However, UAPs often struggle in transferring across DNN architectures
and lead to challenging optimization problems. In this work, we study the
transferability of UAPs by analyzing equilibrium in the universal adversarial
example game between the classifier and UAP adversary players. We show that
under mild assumptions the …

adversarial