DeepAI AI Chat
Log In Sign Up

Improving Adversarial Robustness by Encouraging Discriminative Features

by   Chirag Agarwal, et al.

Deep neural networks (DNNs) have achieved state-of-the-art results in various pattern recognition tasks. However, they perform poorly on out-of-distribution adversarial examples i.e. inputs that are specifically crafted by an adversary to cause DNNs to misbehave, questioning the security and reliability of applications. In this paper, we encourage DNN classifiers to learn more discriminative features by imposing a center loss in addition to the regular softmax cross-entropy loss. Intuitively, the center loss encourages DNNs to simultaneously learns a center for the deep features of each class, and minimize the distances between the intra-class deep features and their corresponding class centers. We hypothesize that minimizing distances between intra-class features and maximizing the distances between inter-class features at the same time would improve a classifier's robustness to adversarial examples. Our results on state-of-the-art architectures on MNIST, CIFAR-10, and CIFAR-100 confirmed that intuition and highlight the importance of discriminative features.


page 1

page 2

page 3

page 4


Contrastive-center loss for deep neural networks

The deep convolutional neural network(CNN) has significantly raised the ...

Adversarial Robustness: Softmax versus Openmax

Deep neural networks (DNNs) provide state-of-the-art results on various ...

Rethinking Softmax Cross-Entropy Loss for Adversarial Robustness

Previous work shows that adversarially robust generalization requires la...

Adaptive Neighbourhoods for the Discovery of Adversarial Examples

Deep Neural Networks (DNNs) have often supplied state-of-the-art results...

Rethinking Feature Distribution for Loss Functions in Image Classification

We propose a large-margin Gaussian Mixture (L-GM) loss for deep neural n...

G-softmax: Improving Intra-class Compactness and Inter-class Separability of Features

Intra-class compactness and inter-class separability are crucial indicat...

Stop memorizing: A data-dependent regularization framework for intrinsic pattern learning

Deep neural networks (DNNs) typically have enough capacity to fit random...