Improving adversarial robustness of deep neural networks by using semantic information

TL;DR

This paper introduces a novel region adversarial training method that leverages semantic information to improve the robustness of deep neural networks against adversarial attacks, especially with limited data.

Contribution

It proposes a new semantic-based adversarial training approach focusing on decision boundary regions, enhancing robustness more effectively than traditional methods.

Findings

Significantly improves adversarial robustness on MNIST and CIFAR-10.

Effective against FGSM attacks with different patterns from training data.

Requires only small datasets for effective training.

Abstract

The vulnerability of deep neural networks (DNNs) to adversarial attack, which is an attack that can mislead state-of-the-art classifiers into making an incorrect classification with high confidence by deliberately perturbing the original inputs, raises concerns about the robustness of DNNs to such attacks. Adversarial training, which is the main heuristic method for improving adversarial robustness and the first line of defense against adversarial attacks, requires many sample-by-sample calculations to increase training size and is usually insufficiently strong for an entire network. This paper provides a new perspective on the issue of adversarial robustness, one that shifts the focus from the network as a whole to the critical part of the region close to the decision boundary corresponding to a given class. From this perspective, we propose a method to generate a single but image-agnostic adversarial perturbation that carries the semantic information implying the directions to the fragile parts on the decision boundary and causes inputs to be misclassified as a specified target. We call the adversarial training based on such perturbations "region adversarial training" (RAT), which resembles classical adversarial training but is distinguished in that it reinforces the semantic information missing in the relevant regions. Experimental results on the MNIST and CIFAR-10 datasets show that this approach greatly improves adversarial robustness even using a very small dataset from the training data; moreover, it can defend against FGSM adversarial attacks that have a completely different pattern from the model seen during retraining.