AI Paper Atlas

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

Random Smoothing Might be Unable to Certify $\ell_\infty$ Robustness for High-Dimensional Images

Avrim Blum, Travis Dick, Naren Manoj, Hongyang Zhang

JMLR 2020 · Adversarial robustness and security › Certified and empirical robustness · approach: Randomized smoothing certification · 37 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 adversarial training with TRADES when training the Gaussian-smoothed base classifierrandom smoothing with ResNet-110 · CIFAR-10 certified l_inf radius 2/255certified robust accuracy (%): 60.8% -> 62.6%Improved
TRADES + random smoothing versus best prior baseline, natural accuracyTRADES + Random Smoothing · CIFAR-10 natural accuracynatural accuracy (%): 82.1% -> 78.8%Hurt
scale input size 32 to 48 to 64 while keeping sigma/(sqrt(d) eps) constant (sigma 0.12, 0.18, 0.24) (ablation)TRADES + random smoothing ResNet-110 · CIFAR-10 resized inputs, certified accuracy curvescertified accuracy vs l_inf radiusNo 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