论文标题
SOAR：二阶对抗正则化
SOAR: Second-Order Adversarial Regularization
论文作者
论文摘要
对抗性训练是提高深神经网络与对抗性例子的鲁棒性的常见方法。在这项工作中，我们提出了一种新颖的正规化方法作为替代方法。为了得出正常化程序，我们在健壮的优化框架下制定了对抗性鲁棒性问题，并使用二阶Taylor系列扩展近似损耗函数。我们提出的二阶对抗正常器（SOAR）是基于内部最大优化目标内部最大近似值的上限。我们从经验上表明，所提出的方法显着提高了网络对$ \ ell_ \ infty $和$ \ ell_2 $有限的扰动的鲁棒性，该扰动在CIFAR-10和SVHN上使用了基于跨凝集的PGD生成。
Adversarial training is a common approach to improving the robustness of deep neural networks against adversarial examples. In this work, we propose a novel regularization approach as an alternative. To derive the regularizer, we formulate the adversarial robustness problem under the robust optimization framework and approximate the loss function using a second-order Taylor series expansion. Our proposed second-order adversarial regularizer (SOAR) is an upper bound based on the Taylor approximation of the inner-max in the robust optimization objective. We empirically show that the proposed method significantly improves the robustness of networks against the $\ell_\infty$ and $\ell_2$ bounded perturbations generated using cross-entropy-based PGD on CIFAR-10 and SVHN.
