Learning Diverse-Structured Networks for Adversarial Robustness

by   Xuefeng Du, et al.

In adversarial training (AT), the main focus has been the objective and optimizer while the model has been less studied, so that the models being used are still those classic ones in standard training (ST). Classic network architectures (NAs) are generally worse than searched NAs in ST, which should be the same in AT. In this paper, we argue that NA and AT cannot be handled independently, since given a dataset, the optimal NA in ST would be no longer optimal in AT. That being said, AT is time-consuming itself; if we directly search NAs in AT over large search spaces, the computation will be practically infeasible. Thus, we propose a diverse-structured network (DS-Net), to significantly reduce the size of the search space: instead of low-level operations, we only consider predefined atomic blocks, where an atomic block is a time-tested building block like the residual block. There are only a few atomic blocks and thus we can weight all atomic blocks rather than find the best one in a searched block of DS-Net, which is an essential trade-off between exploring diverse structures and exploiting the best structures. Empirical results demonstrate the advantages of DS-Net, i.e., weighting the atomic blocks.



There are no comments yet.


page 1

page 2

page 3

page 4


AtomNAS: Fine-Grained End-to-End Neural Architecture Search

Designing of search space is a critical problem for neural architecture ...

Tiny Adversarial Mulit-Objective Oneshot Neural Architecture Search

Due to limited computational cost and energy consumption, most neural ne...

BossNAS: Exploring Hybrid CNN-transformers with Block-wisely Self-supervised Neural Architecture Search

A myriad of recent breakthroughs in hand-crafted neural architectures fo...

An Analysis of Super-Net Heuristics in Weight-Sharing NAS

Weight sharing promises to make neural architecture search (NAS) tractab...

RepNAS: Searching for Efficient Re-parameterizing Blocks

In the past years, significant improvements in the field of neural archi...

Archive Assisted Archival Fixity Verification Framework

The number of public and private web archives has increased, and we impl...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.