AI Paper Atlas

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

Enhancing Adversarial Example Transferability With an Intermediate Level Attack

Qian Huang, Isay Katsman, Horace He, Zeqi Gu, Serge Belongie, Ser-Nam Lim

ICCV 2019 · Adversarial robustness and security › Black-box and transfer attacks · approach: Transferable adversarial examples · 276 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 ILAP refinement targeted at an intermediate layerI-FGSM · CIFAR-10 transfer to GoogLeNet (ResNet18 source)Accuracy after attack: 58.6% -> 35.8%Improved
add ILAP refinementMI-FGSM · CIFAR-10 transfer to SENet18 (ResNet18 source)Accuracy after attack: 33.8% -> 30.6%Improved
add ILAP refinementC&W · CIFAR-10 transfer to SENet18 (ResNet18 source)Accuracy after attack: 85.4% -> 41.7%Improved
add ILAP refinementDeepFool · CIFAR-10 transfer to DenseNet121 (ResNet18 source)Accuracy after attack: 89.1% -> 43.8%Improved
add ILAP refinementFGSM · CIFAR-10 transfer to SENet18 (ResNet18 source)Accuracy after attack: 63.6% -> 42.6%Improved
add ILAP refinementTAP · ImageNet transfer to Inc-v4Accuracy after attack: 21.5% -> 16.3%Improved
add ILAP refinementDI2-FGSM · ImageNet transfer to IncRes-v2Accuracy after attack: 54.6% -> 29.3%Improved
replace projection loss ILAP with flexible loss ILAF (tuned alpha)ILA · CIFAR-10 transfer to SENet18 (ResNet18 source)Accuracy after attack: 27.5% -> 26.3%Improved
10 itr ILAP on MI-FGSM output, same model as source (white-box)MI-FGSM · CIFAR-10 white-box ResNet18Accuracy after attack: 5.7% -> 11.3%Hurt
start ILAP from multi-fool perturbation instead of I-FGSM perturbation (ablation)ILAP · CIFAR-10 (ResNet18 source)Accuracy after attackImproved
add nonlinearity (activations) after extra linear layers before last layer (ablation)ILAP on ResNet18 variants · CIFAR-10 (ResNet18 variants)Accuracy after attackImproved
target later layers with extremely linear decision boundary (ablation)ILAP · CIFAR-10 (ResNet18 source)Accuracy after attackHurt

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