CapsAttacks: Robust and Imperceptible Adversarial Attacks on Capsule Networks

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.

References in corpus (7)

• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• Detecting Adversarial Samples from Artifacts
• Adversarial Examples: Attacks and Defenses for Deep Learning
• CapsNet comparative performance evaluation for image classification
• Novel Deep Learning Model for Traffic Sign Detection Using Capsule Networks
• DARCCC: Detecting Adversaries by Reconstruction from Class Conditional Capsules
• Towards Imperceptible and Robust Adversarial Example Attacks against Neural Networks

Cited by in corpus (7)

• Hardware and Software Optimizations for Accelerating Deep Neural Networks: Survey of Current Trends, Challenges, and the Road Ahead
• Towards Energy-Efficient and Secure Edge AI: A Cross-Layer Framework
• Securing Deep Spiking Neural Networks against Adversarial Attacks through Inherent Structural Parameters
• On the Vulnerability of Capsule Networks to Adversarial Attacks
• Kernelized Capsule Networks
• An Evasion Attack against Stacked Capsule Autoencoder
• Security Analysis of Capsule Network Inference using Horizontal Collaboration