Revisiting Adversarial Training at Scale

arXiv:2401.04727v2 Announce Type: replace
Abstract: The machine learning community has witnessed a drastic change in the training pipeline, pivoted by those ''foundation models'' with unprecedented scales. However, the field of adversarial training is lagging behind, predominantly centered around small model sizes like ResNet-50, and tiny and low-resolution datasets like CIFAR-10. To bridge this transformation gap, this paper provides a modern re-examination with adversarial training, investigating its potential benefits when applied at scale. Additionally, we introduce an efficient and effective training …

abstract adversarial adversarial training arxiv bridge change cifar-10 community cs.cv datasets foundation gap however low machine machine learning pipeline resnet resnet-50 resolution scale small training training pipeline transformation type