On the Vulnerability of Capsule Networks to Adversarial Attacks

2019/06/09 by Félix Michels, Michels, Felix, Tobias Uelwer +5 · 1 citation
Computer Science · #Advanced Malware Detection Techniques #Adversarial Robustness in Machine Learning #Anomaly Detection Techniques and Applications #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)

paper · pdf · doi:10.48550/arxiv.1906.03612

openalex publication_date 2019/06/09 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Citations

• Gradient-based learning applied to document recognition
• Capsule Network Performance on Complex Data
• Dense and Diverse Capsule Networks: Making the Capsules Learn Better
• Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Models
• Learning Multiple Layers of Features from Tiny Images

Cited by

• An Evasion Attack against Stacked Capsule Autoencoder

Related

• CapsAttacks: Robust and Imperceptible Adversarial Attacks on Capsule Networks
• Increasing the adversarial robustness and explainability of capsule networks with γ-capsules
• Deflecting Adversarial Attacks
• An Evasion Attack against Stacked Capsule Autoencoder
• RobCaps: Evaluating the Robustness of Capsule Networks against Affine Transformations and Adversarial Attacks