A2: Efficient Automated Attacker for Boosting Adversarial TrainingDownload PDF

Published: 31 Oct 2022, Last Modified: 12 Mar 2024NeurIPS 2022 AcceptReaders: Everyone
Keywords: Adversarial Training, Automated Machine Learning
Abstract: Based on the significant improvement of model robustness by AT (Adversarial Training), various variants have been proposed to further boost the performance. Well-recognized methods have focused on different components of AT (e.g., designing loss functions and leveraging additional unlabeled data). It is generally accepted that stronger perturbations yield more robust models. However, how to generate stronger perturbations efficiently is still missed. In this paper, we propose an efficient automated attacker called A2 to boost AT by generating the optimal perturbations on-the-fly during training. A2 is a parameterized automated attacker to search in the attacker space for the best attacker against the defense model and examples. Extensive experiments across different datasets demonstrate that A2 generates stronger perturbations with low extra cost and reliably improves the robustness of various AT methods against different attacks.
TL;DR: propose a method called A2 to improve the robustness by constructing the optimal perturbations on-the-fly during training
Supplementary Material: pdf
Community Implementations: [![CatalyzeX](/images/catalyzex_icon.svg) 4 code implementations](https://www.catalyzex.com/paper/arxiv:2210.03543/code)
14 Replies