AI Paper Atlas

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

Boosting Decision-based Black-box Adversarial Attacks with Random Sign Flip

Weilun Chen, Zhaoxiang Zhang, Xiaolin Hu, Baoyuan Wu

ECCV 2020 · Adversarial robustness and security › Black-box and transfer attacks · approach: Query-efficient black-box attacks · 65 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
add random sign flip step (ablation)SFA · CIFAR-10 untargetedattack success rate: 9.1% -> 95.4%Improved
add random sign flip step (ablation)SFA · CIFAR-10 targetedattack success rate: 0.2% -> 99.4%Improved
add dimensionality reduction (ablation)SFA · ImageNet untargeted, Inception-v3attack success rate: 91.1% -> 92.1%Improved
add dimensionality reduction (ablation)SFA · ImageNet untargeted, ResNet-50attack success rate: 96.9% -> 98.2%Improved
add dimensionality reduction (ablation)SFA · ImageNet untargeted, VGG-16attack success rate: 99.0% -> 98.7%Improved
add dimensionality reduction (ablation)SFA · ImageNet targeted, ResNet-50attack success rate: 98.6% -> 99.3%Improved
add dimensionality reduction (ablation)SFA · ImageNet targeted, Inception-v3attack success rate: 97.0% -> 95.8%Hurt
add dimensionality reduction (ablation)SFA · ImageNet targeted, ResNet-50average queries: 29,440 -> 22,538Improved
add dimensionality reduction (ablation)SFA · ImageNet untargeted, VGG-16average queries: 2,112 -> 1,754Improved
use SFA instead of HSJASFA · ImageNet untargeted, Inception-v3attack success rate: 19.4% -> 92.1%Improved
use SFA instead of HSJASFA · ImageNet targeted, Inception-v3attack success rate: 0.0% -> 95.8%Improved
use SFA instead of HSJASFA · CIFAR-10 untargetedattack success rate: 87.1% -> 95.4%Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

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