Active Subspace of Neural Networks: Structural Analysis and Universal Attacks
Chunfeng Cui, Kaiqi Zhang, Talgat Daulbaev, Julia Gusak, Ivan Oseledets, Zheng Zhang
Abstract
Active subspace is a model reduction method widely used in the uncertainty quantification community. In this paper, we propose analyzing the internal structure and vulnerability of deep neural networks using active subspace. Firstly, we employ the active subspace to measure the number of “active neurons” at each intermediate layer, which indicates that the number of neurons can be reduced from several thousands to several dozens. This motivates us to change the network structure and to develop a new and more compact network, referred to as ASNet, that has significantly fewer model parameters. Secondly, we propose analyzing the vulnerability of a neural network using active subspace by finding an additive universal adversarial attack vector that can misclassify a dataset with a high probability. Our experiments on CIFAR-10 show that ASNet can achieve 23.98x parameter and 7.30x flops reduction. The universal active subspace attack vector can achieve around 20% higher attack ratio compared with the existing approaches in our numerical experiments. The PyTorch codes for this paper are available online.