AI Paper Atlas

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

CGBA: Curvature-aware Geometric Black-box Attack

Md Farhamdur Reza, Ali Rahmati, Tianfu Wu, Huaiyu Dai

ICCV 2023 · Adversarial robustness and security › Black-box and transfer attacks · approach: Query-efficient black-box attacks · 32 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
search along a semicircular path in the 2D plane of normal and boundary directions instead of 1-D normal-vector searchdecision-based black-box attack · ImageNet ResNet50 non-targeted, 20000 queriesmedian l2 perturbation: 0.97 (SurFree) -> 0.59 (CGBA)Improved
use CGBA-H (high-curvature variant) instead of CGBA for targeted attacks (ablation)CGBA · ImageNet ResNet50 targeted, 1000 queriesmedian l2 perturbation: 78.99 -> 56.01Improved
use CGBA-H instead of CGBA for non-targeted attacks with small query budget (ablation)CGBA · ImageNet ResNet50 non-targeted, 1000 queriesmedian l2 perturbation: 6.03 -> 5.78Improved
use CGBA-H instead of CGBA for non-targeted attacks with large budget (ablation)CGBA · ImageNet ResNet50 non-targeted, 20000 queriesmedian l2 perturbation: 0.59 -> 0.62Hurt
use CGBA instead of CGBA-H for targeted attack with large budget (ablation)CGBA-H · ImageNet ResNet50 targetedmedian l2 perturbation: CGBA 78.99 at 1000 queries, 5.38 at 20000 vs CGBA-H 56.01, 4.03Mixed
use K=50 target-class samples for initial boundary point instead of random (K=1) (ablation)targeted CGBA · ImageNet targetedinitial perturbation: about 85 -> reduction of more than 30, at about 110 extra queriesImproved
increase dimension reduction factor f for CGBA in frequency subspace (ablation)CGBA · ImageNet non-targetedmedian l2 perturbation: f=4 best at 10000 queries (0.88); f=8 best at 1000 queries (4.72)Mixed
attack adversarially trained ResNet50 with CGBA methodsCGBA · adversarially-trained ResNet50perturbationImproved
CGBA on low-dimensional CIFAR10 targeted attack with large budget (ablation)CGBA-H · CIFAR10 targetedmedian l2 perturbation: WRN40 20000 queries: 0.238 (CGBA-H) -> 0.231 (CGBA)Mixed
CGBA vs SurFree on WRN40 non-targeted at 1000 queriesSurFree · CIFAR10 WRN40 non-targeted, 1000 queriesmedian l2 perturbation: 0.493 (SurFree) vs 0.498 (CGBA)Hurt

Later papers that compared with this method

3 later accepted papers report CGBA as a baseline in their results tables; 3 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