CapsAttacks: Robust and Imperceptible Adversarial Attacks on Capsule Networks

Authors: Alberto Marchisio, Giorgio Nanfa, Faiq Khalid, Muhammad Abdullah Hanif, Maurizio Martina, Muhammad Shafique
Published: 2019-01-28 | Updated: 2019-05-24

Source: https://arxiv.org/abs/1901.09878

PDF: https://arxiv.org/pdf/1901.09878

Labels Predicted by AI

敵対的攻撃 敵対的サンプル 敵対的摂動手法

Please note that these labels were automatically added by AI. Therefore, they may not be entirely accurate.
For more details, please see the About the Literature Database page.

Abstract

Capsule Networks preserve the hierarchical spatial relationships between objects, and thereby bears a potential to surpass the performance of traditional Convolutional Neural Networks (CNNs) in performing tasks like image classification. A large body of work has explored adversarial examples for CNNs, but their effectiveness on Capsule Networks has not yet been well studied. In our work, we perform an analysis to study the vulnerabilities in Capsule Networks to adversarial attacks. These perturbations, added to the test inputs, are small and imperceptible to humans, but can fool the network to mispredict. We propose a greedy algorithm to automatically generate targeted imperceptible adversarial examples in a black-box attack scenario. We show that this kind of attacks, when applied to the German Traffic Sign Recognition Benchmark (GTSRB), mislead Capsule Networks. Moreover, we apply the same kind of adversarial attacks to a 5-layer CNN and a 9-layer CNN, and analyze the outcome, compared to the Capsule Networks to study differences in their behavior.