AI Paper Atlas

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

GeoDA: A Geometric Framework for Black-Box Adversarial Attacks

Ali Rahmati, Seyed-Mohsen Moosavi-Dezfooli, Pascal Frossard, Huaiyu Dai

CVPR 2020 · Adversarial robustness and security › Black-box and transfer attacks · approach: Query-efficient black-box attacks · 108 citations (OpenAlex)

Check 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
Restrict normal-vector queries to a low-frequency DCT subspaceGeoDA · ImageNetmedian ℓ2 perturbation: approximately 27 %Improved
Use an increasing, optimized query allocation across iterations instead of a single-iteration or uniform allocation (ablation)GeoDA · ImageNetℓ2 perturbationImproved
Move the sparse-attack starting point farther across the estimated boundary using ζ (ablation)Sparse GeoDA · ImageNetfooling rate and sparsityMixed
Use a larger query budgetSparse GeoDA · ImageNetsparse adversarial-example performanceImproved

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