arXiv Open Access 2023

Robust Principles: Architectural Design Principles for Adversarially Robust CNNs

ShengYun Peng Weilin Xu Cory Cornelius Matthew Hull Kevin Li +4 lainnya

Lihat Sumber

Abstrak

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.

Topik & Kata Kunci

cs.CV

Penulis (9)

ShengYun Peng

Weilin Xu

Cory Cornelius

Matthew Hull

Kevin Li

Rahul Duggal

Mansi Phute

Jason Martin

Duen Horng Chau

Format Sitasi

APA MLA BibTeX

Peng, S., Xu, W., Cornelius, C., Hull, M., Li, K., Duggal, R. et al. (2023). Robust Principles: Architectural Design Principles for Adversarially Robust CNNs. https://arxiv.org/abs/2308.16258

Akses Cepat

Lihat di Sumber

Informasi Jurnal

Tahun Terbit: 2023
Bahasa: en
Sumber Database: arXiv
Akses: Open Access ✓