On the Vulnerability of Capsule Networks to Adversarial Attacks
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). First posted on arXiv 9 Jun 2019.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 4; 2022: 5; 2023: 2.
11 papers.
- 2021Robust Machine Learning Systems: Challenges, Current Trends, Perspectives, and the Road Aheadcited by 40
- 2022Recognizing Object by Components with Human Prior Knowledge Enhances Adversarial Robustness of Deep Neural Networkscited by 18
- 2021Effective and Efficient Vote Attack on Capsule Networkscited by 14
- 2021Capsule Network is Not More Robust than Convolutional Networkcited by 12
- 2023Why Capsule Neural Networks Do Not Scale: Challenging the Dynamic Parse-Tree Assumptioncited by 6
- 2022The Adversarial Security Mitigations of mmWave Beamforming Prediction Models using Defensive Distillation and Adversarial Retrainingcited by 3
- 2022Defensive Distillation based Adversarial Attacks Mitigation Method for Channel Estimation using Deep Learning Models in Next-Generation Wireless Networkscited by 2
- 2021Security Analysis of Capsule Network Inference using Horizontal Collaborationcited by 1
- 2023RobCaps: Evaluating the Robustness of Capsule Networks against Affine Transformations and Adversarial Attackscited by 1
- 2022Towards Robust Stacked Capsule Autoencoder with Hybrid Adversarial Trainingcited by 0
- 2022Effectiveness of the Recent Advances in Capsule Networkscited by 0
- 2023RobCaps: Evaluating the Robustness of Capsule Networks against Affine Transformations and Adversarial Attacks8 Apr 2023
- 2023Why Capsule Neural Networks Do Not Scale: Challenging the Dynamic Parse-Tree Assumption4 Jan 2023
- 2022Recognizing Object by Components with Human Prior Knowledge Enhances Adversarial Robustness of Deep Neural Networks4 Dec 2022
- 2022Effectiveness of the Recent Advances in Capsule Networks11 Oct 2022
- 2022Defensive Distillation based Adversarial Attacks Mitigation Method for Channel Estimation using Deep Learning Models in Next-Generation Wireless Networks12 Aug 2022
- 2022Towards Robust Stacked Capsule Autoencoder with Hybrid Adversarial Training28 Feb 2022
- 2022The Adversarial Security Mitigations of mmWave Beamforming Prediction Models using Defensive Distillation and Adversarial Retraining16 Feb 2022
- 2021Security Analysis of Capsule Network Inference using Horizontal Collaboration22 Sep 2021
- 2021Capsule Network is Not More Robust than Convolutional Network29 Mar 2021
- 2021Effective and Efficient Vote Attack on Capsule Networks19 Feb 2021
- 2021Robust Machine Learning Systems: Challenges, Current Trends, Perspectives, and the Road Ahead4 Jan 2021