pith. sign in

arxiv: 2006.12834 · v3 · pith:I75KTV5Gnew · submitted 2020-06-23 · 💻 cs.LG · cs.CR· cs.CV· stat.ML

Sparse-RS: a versatile framework for query-efficient sparse black-box adversarial attacks

classification 💻 cs.LG cs.CRcs.CVstat.ML
keywords sparse-rsadversarialattacksblack-boxframeworkmodelspatchessparse
0
0 comments X
read the original 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: $l_0$-bounded perturbations, adversarial patches, and adversarial frames. The $l_0$-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 $20\times20$ adversarial patches and $2$-pixel wide adversarial frames for $224\times224$ images. Finally, we show that Sparse-RS can be applied to generate targeted universal adversarial patches where it significantly outperforms the existing approaches. The code of our framework is available at https://github.com/fra31/sparse-rs.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.