AI Paper Atlas

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

Implicit Euler Skip Connections: Enhancing Adversarial Robustness via Numerical Stability

Mingjie Li, Lingshen He, Zhouchen Lin

ICML 2020 · Adversarial robustness and security › Certified and empirical robustness · approach: Robustness-accuracy trade-off analysis

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 vanilla skip connections with IE-Skips (K=1 inner iteration)ResNet-18 naturally trained on MNIST · MNIST FGSM δ=0.15Robust Acc (%): +2.91 (88.45 to 91.36)Improved
Increase IE-Skips inner iterations from K=1 to K=3 (ablation)IE-ResNet-18 on MNIST · MNIST FGSM δ=0.15Robust Acc (%): +0.91 (91.36 to 92.27)Improved
Replace vanilla skip connections with IE-Skips (K=1)ResNet-50 naturally trained on CIFAR-10 · CIFAR-10 FGSM δ=1/255Robust Acc (%): +0.80 (67.89 to 68.69)Improved
Replace vanilla skip connections with IE-Skips (K=1)PreAct ResNet-18/34/50 with PGD-10 adversarial training on CIFAR-10 · CIFAR-10 PGD-20Robust Acc (%): +1.02 (ResNet-18), +1.22 (ResNet-34), +1.24 (ResNet-50)Improved
Replace vanilla skip connections with IE-Skips (K=1, gamma=0.1) on WideResNet-34 with TRADESWideResNet-34-10 TRADES training on CIFAR-10 · CIFAR-10 PGD-20, PGD-100, C&WRobust Acc (%): +2.56 PGD-20, +3.06 PGD-100, +4.63 C&W vs own reproductionImproved
Replace vanilla skip connections with IE-SkipsResNet-34 with PGD-3 training on CIFAR-10 · CIFAR-10 C&WRobust Acc (%): +0.55 (49.70 to 50.25)Improved
Weight-sharing of adjacent residual blocks (SwResNet-58) instead of IE-SkipsResNet-34 with PGD-3 training on CIFAR-10 · CIFAR-10 C&W and PGD-20Robust Acc (%): -13.73 C&W, -0.09 PGD-20 vs ResNet-34 (SwResNet-58 is deeper)Hurt
Increase inner iterations K of IE-Skips from 0 to 5 (ablation)PreAct ResNet-18 (width 64) with PGD-3 training · CIFAR-10 PGD-20Robust Acc (%): robust accuracy rises from roughly 38 to 42 (figure only)Improved
Increase inner iterations K of IE-Skips (ablation)PreAct ResNet-18 with PGD-3 training · CIFAR-10 natural accuracyNatural Acc (%)No clear effect

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