Robust Universal Adversarial Perturbations. (arXiv:2206.10858v1 [cs.LG])

Web: http://arxiv.org/abs/2206.10858

Universal Adversarial Perturbations (UAPs) are imperceptible, image-agnostic
vectors that cause deep neural networks (DNNs) to misclassify inputs from a
data distribution with high probability. Existing methods do not create UAPs
robust to transformations, thereby limiting their applicability as a real-world
attacks. In this work, we introduce a new concept and formulation of robust
universal adversarial perturbations. Based on our formulation, we build a
novel, iterative algorithm that leverages probabilistic robustness bounds for
generating UAPs robust against transformations generated by composing …

arxiv lg