Sparse-RS: A Versatile Framework for Query-Efficient Sparse Black-Box Adversarial Attacks
Francesco Croce, Maksym Andriushchenko, Naman D. Singh, Nicolas Flammarion, Matthias Hein
Abstract
We propose a versatile framework based on random search, Sparse-RS, for score-based sparse targeted and untargeted attacks in the black-box setting. Sparse-RS does not rely on substitute models and achieves state-of-the-art success rate and query efficiency for multiple sparse attack models: L0-bounded perturbations, adversarial patches, and adversarial frames. The L0-version of untargeted Sparse-RS outperforms all black-box and even all white-box attacks for different models on MNIST, CIFAR-10, and ImageNet. Moreover, our untargeted Sparse-RS achieves very high success rates even for the challenging settings of 20x20 adversarial patches and 2-pixel wide adversarial frames for 224x224 images. Finally, we show that Sparse-RS can be applied to generate targeted universal adversarial patches where it significantly outperforms the existing approaches. Our code is available at https://github.com/fra31/sparse-rs.
BibTeX
@inproceedings{aaai2022_sparsersaversati,
title = {Sparse-RS: A Versatile Framework for Query-Efficient Sparse Black-Box Adversarial Attacks},
author = {Francesco Croce and Maksym Andriushchenko and Naman D. Singh and Nicolas Flammarion and Matthias Hein},
booktitle = {AAAI 2022},
year = {2022}
}