English

Robust Principles: Architectural Design Principles for Adversarially Robust CNNs

Computer Vision and Pattern Recognition 2023-09-04 v2

Abstract

Our research aims to unify existing works' diverging opinions on how architectural components affect the adversarial robustness of CNNs. To accomplish our goal, we synthesize a suite of three generalizable robust architectural design principles: (a) optimal range for depth and width configurations, (b) preferring convolutional over patchify stem stage, and (c) robust residual block design through adopting squeeze and excitation blocks and non-parametric smooth activation functions. Through extensive experiments across a wide spectrum of dataset scales, adversarial training methods, model parameters, and network design spaces, our principles consistently and markedly improve AutoAttack accuracy: 1-3 percentage points (pp) on CIFAR-10 and CIFAR-100, and 4-9 pp on ImageNet. The code is publicly available at https://github.com/poloclub/robust-principles.

Keywords

Cite

@article{arxiv.2308.16258,
  title  = {Robust Principles: Architectural Design Principles for Adversarially Robust CNNs},
  author = {ShengYun Peng and Weilin Xu and Cory Cornelius and Matthew Hull and Kevin Li and Rahul Duggal and Mansi Phute and Jason Martin and Duen Horng Chau},
  journal= {arXiv preprint arXiv:2308.16258},
  year   = {2023}
}

Comments

Published at BMVC'23

R2 v1 2026-06-28T12:08:43.975Z