Whereas adversarial training is employed as the main defence strategy against
specific adversarial samples, it has limited generalization capability and
incurs excessive time complexity. In this paper, we propose an attack-agnostic
defence framework to enhance the intrinsic robustness of neural networks,
without jeopardizing the ability of generalizing clean samples. Our Feature
Pyramid Decoder (FPD) framework applies to all block-based convolutional neural
networks (CNNs). It implants denoising and image restoration modules into a
targeted CNN, and it also constraints the Lipschitz constant of the
classification layer. Moreover, we propose a two-phase strategy to train the
FPD-enhanced CNN, utilizing $\epsilon$-neighbourhood noisy images with
multi-task and self-supervised learning. Evaluated against a variety of
white-box and black-box attacks, we demonstrate that FPD-enhanced CNNs gain
sufficient robustness against general adversarial samples on MNIST, SVHN and
CALTECH. In addition, if we further conduct adversarial training, the
FPD-enhanced CNNs perform better than their non-enhanced versions.

本文提出了一种攻击不可知的防御框架，通过在目标卷积神经网络中嵌入去噪和图像恢复模块以及限制分类层的 Lipschitz 常数来提高神经网络的固有鲁棒性，针对各种白盒和黑盒攻击进行了评估，证明了通过本文所提出的 Feature Pyramid Decoder 增强 CNN 可以获得足够的鲁棒性，特别是当进一步进行对抗训练时，性能比非增强版本更好。