Towards Accurate and Robust Architectures via Neural Architecture Search

arXiv:2405.05502v1 Announce Type: cross
Abstract: To defend deep neural networks from adversarial attacks, adversarial training has been drawing increasing attention for its effectiveness. However, the accuracy and robustness resulting from the adversarial training are limited by the architecture, because adversarial training improves accuracy and robustness by adjusting the weight connection affiliated to the architecture. In this work, we propose ARNAS to search for accurate and robust architectures for adversarial training. First we design an accurate and robust search space, in …

abstract accuracy adjusting adversarial adversarial attacks adversarial training architecture architectures arxiv attacks attention cs.cr cs.cv cs.lg however networks neural architecture search neural networks robust robustness search training type via