Fooling the Big Picture in Classification Tasks.

ABSTRACT: Minimally perturbed adversarial examples were shown to drastically reduce the performance of one-stage classifiers while being imperceptible. This paper investigates the susceptibility of hierarchical classifiers, which use fine and coarse level output categories, to adversarial attacks. We formulate a program that encodes minimax constraints to induce misclassification of the coarse class of a hierarchical classifier (e.g., changing the prediction of a 'monkey' to a 'vehicle' instead of some 'animal'). Subsequently, we develop solutions based on convex relaxations of said program. An algorithm is obtained using the alternating direction method of multipliers with competitive performance in comparison with state-of-the-art solvers. We show the ability of our approach to fool the coarse cla

SUBMITTER: Alkhouri I 

PROVIDER: S-EPMC9638414 | biostudies-literature | 2022 Nov

REPOSITORIES: biostudies-literature