AI Paper Atlas

Research map / Adversarial robustness and security / Certified and empirical robustness

Trust Region Based Adversarial Attack on Neural Networks

Zhewei Yao, Amir Gholami, Peng Xu, Kurt Keutzer, Michael W. Mahoney

CVPR 2019 · Adversarial robustness and security › Certified and empirical robustness · approach: Regularized defenses against attacks · 63 citations (OpenAlex)

Check 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
Apply trust-region attack instead of DeepFoolVGG16 · ImageNet, Linf best-class attackrelative perturbation, average / worst: 0.11% / 4.0% -> 0.10% / 1.4%Improved
Apply trust-region attack instead of FGSMVGG16 · ImageNet, Linf best-class attackrelative perturbation, average / worst: 0.18% / 5.1% -> 0.10% / 1.4%Improved
Apply trust-region attack instead of DeepFoolWResNet · Cifar-10, Linf best-class attackrelative perturbation, average / worst: 0.66% / 3.34% -> 0.56% / 2.67%Improved
Apply trust-region attack instead of FGSMWResNet · Cifar-10, Linf best-class attackrelative perturbation, average / worst: 0.85% / 3.30% -> 0.56% / 2.67%Improved
Apply trust-region attack instead of DeepFoolWResNet · Cifar-10, L2 best-class attackrelative perturbation, average / worst: 0.89% / 5.79% -> 0.73% / 4.43%Improved
Replace fixed TR radius with adaptive radius (ablation)TR attack on VGG16 · ImageNet, Linf best-class attackworst relative perturbation: 1.4% -> 3.4%Hurt
Replace fixed TR radius with adaptive radius (ablation)TR attack on ResNet · Cifar-10, Linf best-class attackaverage relative perturbation: 0.56% -> 0.85%Hurt
Use second-order rather than first-order TR (ablation)TR attack on MLP with Swish · Cifar-10, 10 iterationsaccuracy after attack: 0.27 -> 0.20Improved
Use second-order rather than first-order TR (ablation)TR attack on AlexNet with Swish · Cifar-10, 10 iterationsaccuracy after attack: 0.46 -> 0.44Improved
Use second-order rather than first-order TR (ablation)TR attack on AlexNet with Swish · Cifar-10, 2 iterationsaccuracy after attack: 28.17 -> 26.97Improved
Use second-order rather than first-order TR (ablation)TR attack on MLP with Swish · Cifar-10, 2 iterationsaccuracy after attack: 33.7 -> 33.37Mixed

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