GEOMETRIC AUGMENTATION FOR ROBUST NEURAL NETWORK CLASSIFIERS

Robert M. Taylor, Yusong Tan

Abstract: We introduce a novel geometric perspective and unsupervised model augmentation framework for transforming traditional deep (convolutional) neural networks into adversarially robust classifiers. Class-conditional probability densities based on Bayesian nonparametric mixtures of factor analyzers (BNP-MFA) over the input space are used to design soft decision labels for feature to label isometry. Classconditional distributions over features are also learned using BNP-MFA to develop plug-in maximum a posterior (MAP) classifiers to replace the traditional multinomial logistic softmax classification layers. This novel unsupervised augmented framework, which we call geometrically robust networks (GRN), is applied to CIFAR-10, CIFAR-100, and to Radio-ML (a time series dataset for radio modulation recognition). We demonstrate the robustness of GRN models to adversarial attacks from fast gradient sign method, Carlini-Wagner, and projected gradient descent.

Keywords: Bayesian nonparametric, robust, deep neural network, classifier, unsupervised learning, geometric

TL;DR: We develop a statistical-geometric unsupervised learning augmentation framework for deep neural networks to make them robust to adversarial attacks.