Automated Robustness with Adversarial Training as a Post-Processing Step
Abstract
Adversarial training is a computationally expensive task and hence searching for neural network architectures with robustness as the criterion can be challenging. As a step towards practical automation, this work explores the efficacy of a simple post processing step in yielding robust deep learning model. To achieve this, we adopt adversarial training as a post-processing step for optimised network architectures obtained from a neural architecture search algorithm. Specific policies are adopted for tuning the hyperparameters of the different steps, resulting in a fully automated pipeline for generating adversarially robust deep learning models. We evidence the usefulness of the proposed pipeline with extensive experimentation across 11 image classification and 9 text classification tasks.
Cite
@article{arxiv.2109.02532,
title = {Automated Robustness with Adversarial Training as a Post-Processing Step},
author = {Ambrish Rawat and Mathieu Sinn and Beat Buesser},
journal= {arXiv preprint arXiv:2109.02532},
year = {2021}
}