AI Paper Atlas

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

An Intermediate-level Attack Framework on The Basis of Linear Regression

Yiwen Guo, Qizhang Li, Wangmeng Zuo, Hao Chen

TPAMI 2022 · Adversarial robustness and security › Black-box and transfer attacks · approach: Transferable adversarial examples · 10 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 linear-regression intermediate-level guidance (RR, ILA++) on top of I-FGSMI-FGSM · ImageNet untargeted l_inf eps=8/255avg attack success rate: 27.46% -> 63.38%Improved
replace ILA with the regression-based ILA++I-FGSM+ILA · ImageNet untargeted l_inf eps=8/255avg attack success rate: 60.02% -> 63.38%Improved
maximize intermediate-level feature magnitude instead of normalizing the discrepancy (ablation)I-FGSM+RR · ImageNet untargeted l_inf eps=16/255avg attack success rate: 31.48% -> 88.57%Improved
maximize intermediate-level feature magnitude instead of normalizing the discrepancy (ablation)I-FGSM+RR · ImageNet untargeted l2 eps=15avg attack success rate: 63.54% -> 87.66%Improved
use baseline-derived adversarial directional guide instead of random input-space guide (ablation)I-FGSM+RR · ImageNet untargeted l_inf eps=8/255avg attack success rate: 21.25% -> 63.38%Improved
draw random guide in input space instead of feature space (ablation)Rand+RR · ImageNet untargeted l_inf eps=8/255avg attack success rate: 12.26% -> 21.25%Improved
use SVR instead of ridge regressionI-FGSM+RR · ImageNet untargeted l_inf eps=8/255avg attack success rate: 63.38% -> 64.01%Improved
use SVR instead of ridge regressionI-FGSM+RR · ImageNet untargeted l2 eps=10avg attack success rate: 74.78% -> 75.31%Improved
use ElasticNet instead of ridge regressionI-FGSM+RR · ImageNet untargeted l_inf eps=8/255avg attack success rate: 63.38% -> 50.07%Hurt
decrease ElasticNet lambda1 from 1.0 to 0.05 (ablation)I-FGSM+ElasticNet · ImageNet untargeted l_inf eps=8/255avg attack success rate: 31.97% -> 50.07%Improved
decrease ElasticNet lambda1 from 1.0 to 0.05 (source model ResNet-50) (ablation)I-FGSM+ElasticNet · ImageNet untargeted l_inf eps=8/255 (source model)avg attack success rate: 98.16% -> 99.92%Improved
collect guides from 10 random-init PGD runs with SVRI-FGSM+SVR · ImageNet untargeted l_inf eps=8/255avg attack success rate: 64.01% -> 66.14%Improved

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