Active Subspace of Neural Networks: Structural Analysis and Universal Attacks

DOI10.1137/19M1296070zbMath1486.90152arXiv1910.13025OpenAlexW3095125464MaRDI QIDQ5037556

T. Daulbaev, Kaiqi Zhang, Chunfeng Cui, Ivan V. Oseledets, Zheng Zhang, Julia Gusak

Publication date: 1 March 2022

Published in: SIAM Journal on Mathematics of Data Science (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1910.13025

zbMATH Keywords

network reductiondeep neural networkactive subspaceuniversal adversarial perturbation

Mathematics Subject Classification ID

Nonparametric robustness (62G35) Nonconvex programming, global optimization (90C26) Eigenvalues, singular values, and eigenvectors (15A18)

Related Items (4)

Kernel‐based active subspaces with application to computational fluid dynamics parametric problems using the discontinuous Galerkin method ⋮ On the Deep Active-Subspace Method ⋮ Model-independent detection of new physics signals using interpretable semisupervised classifier tests ⋮ A Supervised Learning Approach Involving Active Subspaces for an Efficient Genetic Algorithm in High-Dimensional Optimization Problems

Uses Software

• aplore3
• DeepFool
• ImageNet
• Adam
• GXNOR-Net
• BinaryNet
• AMC
• AlexNet
• FitNets
• ProxylessNAS

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Finding structure with randomness: Probabilistic algorithms for constructing approximate matrix decompositions
• FitNets
• Modeling uncertainty in steady state diffusion problems via generalized polynomial chaos
• GXNOR-Net: training deep neural networks with ternary weights and activations without full-precision memory under a unified discretization framework
• Exploiting active subspaces to quantify uncertainty in the numerical simulation of the hyshot II scramjet
• Minimization of functions having Lipschitz continuous first partial derivatives
• Frequent Directions: Simple and Deterministic Matrix Sketching
• Active Subspaces
• Nonmonotone Spectral Projected Gradient Methods on Convex Sets
• The Wiener--Askey Polynomial Chaos for Stochastic Differential Equations
• Applied Logistic Regression
• Erratum: Active Subspace Methods in Theory and Practice: Applications to Kriging Surfaces
• Accelerated proximal stochastic dual coordinate ascent for regularized loss minimization

This page was built for publication: Active Subspace of Neural Networks: Structural Analysis and Universal Attacks