Exploiting Joint Robustness to Adversarial Perturbations

Ali Dabouei

Abstract:

Recently, ensemble models have demonstrated empirical
capabilities to alleviate the adversarial vulnerability. In this
paper, we exploit first-order interactions within ensembles to
formalize a reliable and practical defense. We introduce a
scenario of interactions that certifiably improves the robustness according to the size of the ensemble, the diversity of
the gradient directions, and the balance of the member’s contribution to the robustness. We present a joint gradient phase
and magnitude regularization (GPMR) as a vigorous approach to impose the desired scenario of interactions among
members of the ensemble. Through extensive experiments,
including gradient-based and gradient-free evaluations on
several datasets and network architectures, we validate the
practical effectiveness of the proposed approach compared
to the previous methods. Furthermore, we demonstrate that
GPMR is orthogonal to other defense strategies developed
for single classifiers and their combination can further improve the robustness of ensembles.