On the Vulnerability of Capsule Networks to Adversarial Attacks

06/09/2019

∙

This paper extensively evaluates the vulnerability of capsule networks to different adversarial attacks. Recent work suggests that these architectures are more robust towards adversarial attacks than other neural networks. However, our experiments show that capsule networks can be fooled as easily as convolutional neural networks.

READ FULL TEXT

On the Vulnerability of Capsule Networks to Adversarial Attacks

CapsAttacks: Robust and Imperceptible Adversarial Attacks on Capsule Networks

Adversarial attacks hidden in plain sight

Understanding (Non-)Robust Feature Disentanglement and the Relationship Between Low- and High-Dimensional Adversarial Attacks

Exploiting Vulnerability of Pooling in Convolutional Neural Networks by Strict Layer-Output Manipulation for Adversarial Attacks

Universal Adversarial Attacks with Natural Triggers for Text Classification

A Deep, Information-theoretic Framework for Robust Biometric Recognition

Requirements for Developing Robust Neural Networks

On the Vulnerability of Capsule Networks to Adversarial Attacks

Related Research

CapsAttacks: Robust and Imperceptible Adversarial Attacks on Capsule Networks

Adversarial attacks hidden in plain sight

Understanding (Non-)Robust Feature Disentanglement and the Relationship Between Low- and High-Dimensional Adversarial Attacks

Exploiting Vulnerability of Pooling in Convolutional Neural Networks by Strict Layer-Output Manipulation for Adversarial Attacks

Universal Adversarial Attacks with Natural Triggers for Text Classification

A Deep, Information-theoretic Framework for Robust Biometric Recognition

Requirements for Developing Robust Neural Networks