On the Vulnerability of Capsule Networks to Adversarial Attacks

Abstract

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.

arXiv comment5 pages

References in corpus (6)

• Adam: A Method for Stochastic Optimization
• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• Capsule Network Performance on Complex Data
• Dense and Diverse Capsule Networks: Making the Capsules Learn Better
• DARCCC: Detecting Adversaries by Reconstruction from Class Conditional Capsules
• CapsAttacks: Robust and Imperceptible Adversarial Attacks on Capsule Networks

Cited by in corpus (4)

• Detecting and Diagnosing Adversarial Images with Class-Conditional Capsule Reconstructions
• Effective and Efficient Vote Attack on Capsule Networks
• An Evasion Attack against Stacked Capsule Autoencoder
• Security Analysis of Capsule Network Inference using Horizontal Collaboration