On the Need for Topology-Aware Generative Models for Manifold-Based Defenses
arXiv:1909.03334
Abstract
Machine-learning (ML) algorithms or models, especially deep neural networks (DNNs), have shown significant promise in several areas. However, researchers have recently demonstrated that ML algorithms, especially DNNs, are vulnerable to adversarial examples (slightly perturbed samples that cause misclassification). The existence of adversarial examples has hindered the deployment of ML algorithms in safety-critical sectors, such as security. Several defenses for adversarial examples exist in the literature. One of the important classes of defenses are manifold-based defenses, where a sample is ``pulled back" into the data manifold before classifying. These defenses rely on the assumption that data lie in a manifold of a lower dimension than the input space. These defenses use a generative model to approximate the input distribution. In this paper, we investigate the following question: do the generative models used in manifold-based defenses need to be topology-aware? We suggest the answer is yes, and we provide theoretical and empirical evidence to support our claim.
References in corpus (20)
- Adam: A Method for Stochastic Optimization
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- Ensemble Adversarial Training: Attacks and Defenses
- Towards Deep Learning Models Resistant to Adversarial Attacks
- Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples
- Energy-based Generative Adversarial Network
- Density estimation using Real NVP
- Certified Defenses against Adversarial Examples
- Countering Adversarial Images using Input Transformations
- Detecting Adversarial Samples from Artifacts
- Certifying Some Distributional Robustness with Principled Adversarial Training
- PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examples
- Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Models
- Stochastic Activation Pruning for Robust Adversarial Defense
- Mitigating Adversarial Effects Through Randomization
- A Boundary Tilting Persepective on the Phenomenon of Adversarial Examples
- FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Models
- The Robust Manifold Defense: Adversarial Training using Generative Models
- Monge-Ampère Flow for Generative Modeling
- The Mean and Median Criterion for Automatic Kernel Bandwidth Selection for Support Vector Data Description