Are Generative Classifiers More Robust to Adversarial Attacks?

Abstract

There is a rising interest in studying the robustness of deep neural network classifiers against adversaries, with both advanced attack and defence techniques being actively developed. However, most recent work focuses on discriminative classifiers, which only model the conditional distribution of the labels given the inputs. In this paper, we propose and investigate the deep Bayes classifier, which improves classical naive Bayes with conditional deep generative models. We further develop detection methods for adversarial examples, which reject inputs with low likelihood under the generative model. Experimental results suggest that deep Bayes classifiers are more robust than deep discriminative classifiers, and that the proposed detection methods are effective against many recently proposed attacks.

arXiv commentICML 2019

References in corpus (20)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Auto-Encoding Variational Bayes
• Ensemble Adversarial Training: Attacks and Defenses
• Conditional Image Generation with PixelCNN Decoders
• ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Models
• Pixel Recurrent Neural Networks
• Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples
• Towards Deep Neural Network Architectures Robust to Adversarial Examples
• Security Evaluation of Pattern Classifiers under Attack
• Adversarial Risk and the Dangers of Evaluating Against Weak Attacks
• Detecting Adversarial Samples from Artifacts
• On the (Statistical) Detection of Adversarial Examples
• Towards the first adversarially robust neural network model on MNIST
• Multiplicative Normalizing Flows for Variational Bayesian Neural Networks
• On Causal and Anticausal Learning
• Dropout Inference in Bayesian Neural Networks with Alpha-divergences
• Adversarial Images for Variational Autoencoders
• Adversarial examples for generative models
• GenAttack: Practical Black-box Attacks with Gradient-Free Optimization
• LatentPoison - Adversarial Attacks On The Latent Space

Cited by in corpus (7)

• Going in circles is the way forward: the role of recurrence in visual inference
• Your Classifier is Secretly an Energy Based Model and You Should Treat it Like One
• Machine Learning in NextG Networks via Generative Adversarial Networks
• A Causal View on Robustness of Neural Networks
• Anomalous Example Detection in Deep Learning: A Survey
• Dimensionality reduction, regularization, and generalization in overparameterized regressions
• Reject Illegal Inputs with Generative Classifier Derived from Any Discriminative Classifier