Defending Adversarial Examples by Negative Correlation Ensemble
This addresses security risks in deep learning by enhancing defense against adversarial attacks, though it appears incremental as it builds on existing ensemble methods.
The paper tackles the problem of adversarial examples in deep neural networks by proposing a Negative Correlation Ensemble (NCEn) defense approach, which improves adversarial robustness by making gradient directions and magnitudes negatively correlated among ensemble members and reducing adversarial transferability.
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.