AI Paper Atlas

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

Adversarial Rademacher Complexity of Deep Neural Networks

Jiancong Xiao, Yanbo Fan, Ruoyu Sun, Zhi-Quan Luo

JMLR 2026 · Adversarial robustness and security › Certified and empirical robustness · approach: Robust overfitting and regularization

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
use adversarial training instead of standard trainingVGG-19 · CIFAR-10 standard generalization gapgeneralization gap: 10.45% -> 26.34%Hurt
evaluate robust instead of standard gap for adversarially-trained modelVGG-19 adversarial training · CIFAR-10generalization gap: 26.34% -> 58.90%Hurt
increase weight decay (reduce weight norms) (ablation)VGG adversarial training · CIFAR-10/100robust generalizationMixed
use adversarial instead of standard training on weight norm ratioVGG models · CIFAR-10 and CIFAR-100normalized weight norm productHurt

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