On the Properties of Adversarially-Trained CNNs
Adversarial Training has proved to be an effective training paradigm to enforce robustness against adversarial examples in modern neural network architectures. Despite many efforts, explanations of the foundational principles underpinning the effectiveness of Adversarial Training are limited and far from being widely accepted by the Deep Learning community. In this paper, we describe surprising properties of adversarially-trained models, shedding light on mechanisms through which robustness against adversarial attacks is implemented. Moreover, we highlight limitations and failure modes affecting these models that were not discussed by prior works. We conduct extensive analyses on a wide range of architectures and datasets, performing a deep comparison between robust and natural models.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Sparta: Spatially Attentive and Adversarially Robust Activation
Adversarial training (AT) is one of the most effective ways for improving the robustness of deep convolution neural networks (CNNs). Just like common network training, the effectiveness of AT relies on the design of basi…
Large Norms of CNN Layers Do Not Hurt Adversarial Robustness
Since the Lipschitz properties of convolutional neural networks (CNNs) are widely considered to be related to adversarial robustness, we theoretically characterize the $\ell_1$ norm and $\ell_\infty$ norm of 2D multi-cha…
Adversarial RobustnessThe shape and simplicity biases of adversarially robust ImageNet-trained CNNs
Increasingly more similarities between human vision and convolutional neural networks (CNNs) have been revealed in the past few years. Yet, vanilla CNNs often fall short in generalizing to adversarial or out-of-distribut…
Image GenerationInterpreting Adversarially Trained Convolutional Neural Networks
We attempt to interpret how adversarially trained convolutional neural networks (AT-CNNs) recognize objects. We design systematic approaches to interpret AT-CNNs in both qualitative and quantitative ways and compare them…
Object RecognitionImproving Global Adversarial Robustness Generalization With Adversarially Trained GAN
Convolutional neural networks (CNNs) have achieved beyond human-level accuracy in the image classification task and are widely deployed in real-world environments. However, CNNs show vulnerability to adversarial perturba…
Adversarial DefenseAdversarial RobustnessData Augmentationimage-classification+1