Ensemble-based Adversarial Defense Using Diversified Distance Mapping

Ehsan Kazemi, Mohamed E. Hussein, Wael AbdAlmageed

Keywords: adversarial machine learning, ensemble, mahalanobis distance

Abstract: We propose an ensemble-based defense against adversarial examples using distance map layers (DMLs). Similar to fully connected layers, DMLs can be used to output logits for a multi-class classification model. We show in this paper how DMLs can be deployed to prevent transferability of attacks across ensemble members by adapting pairwise (almost) orthogonal covariance matrices. We also illustrate how DMLs provide an efficient way to regularize the Lipschitz constant of the ensemble's member models, which further boosts the resulting robustness. Through empirical evaluations across multiple datasets and attack models, we demonstrate that the ensembles based on DMLs can achieve high benign accuracy while exhibiting robustness against adversarial attacks using multiple white-box techniques along with AutoAttack.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Reviewed Version (pdf): https://openreview.net/references/pdf?id=2ewpGar0dSG