Are Generative Classifiers More Robust to Adversarial Attacks?
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.
Code (1)
Tasks
Adversarial DefenseAdversarial RobustnessSimilar Papers 제목 키워드 기반
Poisoning Attacks with Generative Adversarial Nets
Machine learning algorithms are vulnerable to poisoning attacks: An adversary can inject malicious points in the training dataset to influence the learning process and degrade the algorithm's performance. Optimal poisoni…
BIG-bench Machine LearningData PoisoningGenerating Universal Adversarial Perturbations for Quantum Classifiers
Quantum Machine Learning (QML) has emerged as a promising field of research, aiming to leverage the capabilities of quantum computing to enhance existing machine learning methodologies. Recent studies have revealed that,…
Quantum Machine LearningREGroup: Rank-aggregating Ensemble of Generative Classifiers for Robust Predictions
Deep Neural Networks (DNNs) are often criticized for being susceptible to adversarial attacks. Most successful defense strategies adopt adversarial training or random input transformations that typically require retraini…
Adversarial AttackMinimax Defense against Gradient-based Adversarial Attacks
State-of-the-art adversarial attacks are aimed at neural network classifiers. By default, neural networks use gradient descent to minimize their loss function. The gradient of a classifier's loss function is used by grad…
Generative Adversarial NetworkTowards Understanding the Generative Capability of Adversarially Robust Classifiers
Recently, some works found an interesting phenomenon that adversarially robust classifiers can generate good images comparable to generative models. We investigate this phenomenon from an energy perspective and provide a…
Image Generation