Defending Adversarial Examples by Negative Correlation Ensemble

TL;DR

This paper introduces the Negative Correlation Ensemble (NCEn), a novel defense method that enhances the robustness of deep neural networks against adversarial examples by negatively correlating ensemble members' gradients.

Contribution

The paper proposes a new ensemble defense approach that reduces transferability of adversarial examples by negatively correlating gradient directions and magnitudes of ensemble members.

Findings

NCEn improves adversarial robustness effectively.

Ensemble members' gradients are negatively correlated.

Experimental results demonstrate superior defense performance.

Abstract

The security issues in DNNs, such as adversarial examples, have attracted much attention. Adversarial examples refer to the examples which are capable to induce the DNNs return completely predictions by introducing carefully designed perturbations. Obviously, adversarial examples bring great security risks to the development of deep learning. Recently, Some defense approaches against adversarial examples have been proposed, however, in our opinion, the performance of these approaches are still limited. In this paper, we propose a new ensemble defense approach named the Negative Correlation Ensemble (NCEn), which achieves compelling results by introducing gradient directions and gradient magnitudes of each member in the ensemble negatively correlated and at the same time, reducing the transferability of adversarial examples among them. Extensive experiments have been conducted, and the results demonstrate that NCEn can improve the adversarial robustness of ensembles effectively.