AI Paper Atlas

Research map / Adversarial robustness and security / Black-box and transfer attacks

Square Attack: a query-efficient black-box adversarial attack via random search

Maksym Andriushchenko, Francesco Croce, Nicolas Flammarion, Matthias Hein

ECCV 2020 · Adversarial robustness and security › Black-box and transfer attacks · approach: Query-efficient black-box attacks · 979 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use square-shaped updates instead of random pixel positions (c signs) (ablation)l_inf Square Attack · ImageNet ResNet-50 l_inf eps=0.05avg queries: 339 -> 73Improved
use square-shaped updates instead of random pixel positions (c*h^2 signs) (ablation)l_inf Square Attack · ImageNet ResNet-50 l_inf eps=0.05avg queries: 401 -> 153Improved
use one sign per color channel instead of independent signs per pixel (ablation)l_inf Square Attack · ImageNet ResNet-50 l_inf eps=0.05avg queries: 153 -> 73Improved
use square instead of rectangle updates (ablation)l_inf Square Attack · ImageNet ResNet-50 l_inf eps=0.05avg queries: 93 -> 73Improved
use vertical stripes initialization instead of uniform random (ablation)l_inf Square Attack · ImageNet ResNet-50 l_inf eps=0.05avg queries: 91 -> 73Improved
use vertical stripes initialization instead of uniform random (ablation)l_inf Square Attack · ImageNet ResNet-50 l_inf eps=0.05median queries: 26 -> 11Improved
use vertical stripes instead of horizontal stripes initialization (ablation)l_inf Square Attack · ImageNet ResNet-50 l_inf eps=0.05avg queries: 83 -> 73Improved
use one sign per color channel instead of a single sign for all elements (ablation)l_inf Square Attack · ImageNet ResNet-50 l_inf eps=0.05avg queries: 129 -> 73Improved
use one sign per square instead of independent signs per element (ablation)l_2 Square Attack · ImageNet ResNet-50 l_2 eps=5avg queries: 1050 -> 616Improved
use two-center update eta instead of single-center eta (ablation)l_2 Square Attack · ImageNet ResNet-50 l_2 eps=5avg queries: 650 -> 616Improved
change the l_2 initialization (gaussian, uniform or vertical stripes instead of eta-grid) (ablation)l_2 Square Attack · ImageNet ResNet-50 l_2 eps=5avg queries: 696 / 660 / 655 vs 616No clear effect
vary initial square fraction p from 0.0125 to 0.4 (ablation)l_inf Square Attack · ImageNet ResNet-50 l_inf eps=0.05failure rate / avg queries: 0.0% failure, below 140 avg queriesNo clear effect

Later papers that compared with this method

4 later accepted papers report Square Attack as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy