Showing cs.CVShow all
2 papers · 1 filter
cs.CV2020
Vulnerability of deep neural networks for detecting COVID-19 cases from chest X-ray images to universal adversarial attacks
Hokuto Hirano, Kazuki Koga, Kazuhiro Takemoto
Under the epidemic of the novel coronavirus disease 2019 (COVID-19), chest X-ray computed tomography imaging is being used for effectively screening COVID-19 patients. The developm…
cs.CV2019
Simple iterative method for generating targeted universal adversarial perturbations
Hokuto Hirano, Kazuhiro Takemoto
Deep neural networks (DNNs) are vulnerable to adversarial attacks. In particular, a single perturbation known as the universal adversarial perturbation (UAP) can foil most classifi…