AI Paper Atlas

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

Training Meta-Surrogate Model for Transferable Adversarial Attack

Yunxiao Qin, Yuanhao Xiong, Jinfeng Yi, Cho-Jui Hsieh

AAAI 2023 · Adversarial robustness and security › Black-box and transfer attacks · approach: Transferable adversarial examples · 24 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
train and attack a meta-surrogate rather than attack the original surrogate directlyCIFAR-10 transfer attack · CIFAR-10, MobileNet-V3attack success rate: 90.8% -> 91.8%Improved
train and attack a meta-surrogate rather than attack the original surrogate directlyCIFAR-10 transfer attack · CIFAR-10, adversarially trained ResNet-18attack success rate: 96.1% -> 98.4%Improved
train and attack a meta-surrogate rather than attack the original surrogate directlyImageNet transfer attack · ImageNet, Inc-V3 ens3attack success rate: 71.1% -> 75.5%Improved
add the arctan gradient component to Customized PGD (ablation)MTA-PGD · CIFAR-10, MobileNet-V3attack success rate: 70.0% -> 91.8%Improved
add the sign gradient component to Customized PGD (ablation)MTA-PGD · CIFAR-10, MobileNet-V3attack success rate: 90.0% -> 91.8%Improved
replace ResNet-13 with DenseNet-22BC as the MSM backbone (ablation)MTA-PGD · CIFAR-10, MobileNet-V3attack success rate: 91.8% -> 86.9%Hurt
use PGD-L2 instead of Customized PGD during MSM training (ablation)MTA-PGD · CIFAR-10, MobileNet-V3attack success rate: 80.8% -> 91.8%Hurt
use PGD-L1 instead of Customized PGD during MSM training (ablation)MTA-PGD · CIFAR-10, MobileNet-V3attack success rate: 81.5% -> 91.8%Hurt
increase γ1 from 0.01 to 0.05 (ablation)Customized PGD training for MTA-PGD · CIFAR-10, MobileNet-V3attack success rate: 90.5% vs 91.8%Hurt
increase γ2 from 0.01 to 0.05 (ablation)Customized PGD training for MTA-PGD · CIFAR-10, MobileNet-V3attack success rate: 86.7% vs 91.8%Hurt
increase the number of training attack steps from below 7 toward 7 (ablation)MTA-PGD · CIFAR-10 target modelsattack success rateImproved
increase the number of training attack steps beyond 7 (ablation)MTA-PGD · CIFAR-10 target modelsattack success rateHurt

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