AI Paper Atlas

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

Robust Neural Networks inspired by Strong Stability Preserving Runge-Kutta methods

Byungjoo Kim, Bryce Chudomelka, Jinyoung Park, Jaewoo Kang, Youngjoon Hong, Hyunwoo J. Kim

ECCV 2020 · Adversarial robustness and security › Certified and empirical robustness · approach: Robustness-accuracy trade-off analysis · 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
replace ResBlock with SSP-3 blockResNet · MNIST (standard training)PGD20 accuracy: 0.5799 -> 0.6176Improved
replace ResBlock with SSP-2 blockResNet · MNIST (standard training)PGD20 accuracy: 0.5799 -> 0.5979Improved
replace ResBlock with adaptive Runge-Kutta block (ArkBlock)ResNet · MNIST (standard training)PGD30 accuracy: 0.1773 -> 0.5102Improved
replace ResBlock with ArkBlockResNet · MNIST (standard training)clean accuracy: 0.9961 -> 0.9946No clear effect
replace ResBlock with SSP-2ResNet · CIFAR10 adversarial training (N=6, K=7)PGD20 accuracy: 0.4150 -> 0.4368Improved
replace ResBlock with SSP-adapResNet · CIFAR10 adversarial training (N=10, K=7)natural and PGD20 accuracy: 0.4111 -> 0.4310Improved
replace ResBlock with SSP-adapResNet · CIFAR10 adversarial training (N=6, K=12)PGD20 accuracy: 0.4650 -> 0.4943Improved
use mid-RK2 block (second-order, not SSP) instead of ResBlock (ablation)ResNet · CIFAR10 adversarial trainingPGD20 accuracy: 0.4150 -> 0.4129No clear effect
add SSP property to second-order scheme (SSP-2 vs mid-RK2) (ablation)mid-RK2 · CIFAR10 adversarial training (N=6, K=7)PGD20 accuracy: 0.4129 -> 0.4368Improved
train with stronger PGD (K=12 instead of 7) in adversarial training (ablation)SSP-3 (N=6) · CIFAR10PGD20 accuracy: 0.4246 -> 0.4976Improved
increase number of blocks N from 6 to 10 (ablation)SSP-3 (K=7) · CIFAR10 adversarial trainingPGD20 accuracy: 0.4246 -> 0.4497Improved
replace ResBlock with SSP-3ResNet · CIFAR10 adversarial training, FGSM eps=8FGSM accuracy: 42.29 -> 45.40Improved

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