An Evasion Attack against Stacked Capsule Autoencoder

TL;DR

This paper presents a novel evasion attack on the Stacked Capsule Autoencoder (SCAE), revealing its vulnerability to adversarial perturbations that can cause misclassification without altering the original image structure.

Contribution

The paper introduces the first evasion attack targeting SCAE, demonstrating its security weaknesses and potential for adversarial exploitation.

Findings

High success rate of the attack in fooling SCAE

Stealthy perturbations that do not alter image structure

SCAE's vulnerability to adversarial samples

Abstract

Capsule network is a type of neural network that uses the spatial relationship between features to classify images. By capturing the poses and relative positions between features, its ability to recognize affine transformation is improved, and it surpasses traditional convolutional neural networks (CNNs) when handling translation, rotation and scaling. The Stacked Capsule Autoencoder (SCAE) is the state-of-the-art capsule network. The SCAE encodes an image as capsules, each of which contains poses of features and their correlations. The encoded contents are then input into the downstream classifier to predict the categories of the images. Existing research mainly focuses on the security of capsule networks with dynamic routing or EM routing, and little attention has been given to the security and robustness of the SCAE. In this paper, we propose an evasion attack against the SCAE. After a perturbation is generated based on the output of the object capsules in the model, it is added to an image to reduce the contribution of the object capsules related to the original category of the image so that the perturbed image will be misclassified. We evaluate the attack using an image classification experiment, and the experimental results indicate that the attack can achieve high success rates and stealthiness. It confirms that the SCAE has a security vulnerability whereby it is possible to craft adversarial samples without changing the original structure of the image to fool the classifiers. We hope that our work will make the community aware of the threat of this attack and raise the attention given to the SCAE's security.