A Useful Taxonomy for Adversarial Robustness of Neural Networks

Abstract

Adversarial attacks and defenses are currently active areas of research for the deep learning community. A recent review paper divided the defense approaches into three categories; gradient masking, robust optimization, and adversarial example detection. We divide gradient masking and robust optimization differently: (1) increasing intra-class compactness and inter-class separation of the feature vectors improves adversarial robustness, and (2) marginalization or removal of non-robust image features also improves adversarial robustness. By reframing these topics differently, we provide a fresh perspective that provides insight into the underlying factors that enable training more robust networks and can help inspire novel solutions. In addition, there are several papers in the literature of adversarial defenses that claim there is a cost for adversarial robustness, or a trade-off between robustness and accuracy but, under this proposed taxonomy, we hypothesis that this is not universal. We follow up on our taxonomy with several challenges to the deep learning research community that builds on the connections and insights in this paper.

arXiv commentNRL Technical Report

References in corpus (21)

• Intriguing properties of neural networks
• Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples
• Adversarially Robust Generalization Requires More Data
• Countering Adversarial Images using Input Transformations
• Adversarial Examples Are Not Bugs, They Are Features
• Detecting Adversarial Samples from Artifacts
• Robustness May Be at Odds with Accuracy
• PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examples
• Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Models
• Defensive Distillation is Not Robust to Adversarial Examples
• Stochastic Activation Pruning for Robust Adversarial Defense
• Are Labels Required for Improving Adversarial Robustness?
• Provably Minimally-Distorted Adversarial Examples
• Evaluating and Understanding the Robustness of Adversarial Logit Pairing
• Adversarial Robustness May Be at Odds With Simplicity
• Adversarial Manipulation of Deep Representations
• $\mathcal{G}$-softmax: Improving Intra-class Compactness and Inter-class Separability of Features
• Batch Normalization is a Cause of Adversarial Vulnerability
• Towards Understanding Adversarial Examples Systematically: Exploring Data Size, Task and Model Factors
• Understanding Adversarial Robustness: The Trade-off between Minimum and Average Margin
• Adversarial Defense by Suppressing High-frequency Components

Cited by in corpus (1)

• Deep Repulsive Prototypes for Adversarial Robustness