AI Paper Atlas

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

A Bayes-Optimal View on Adversarial Examples

Eitan Richardson, Yair Weiss

JMLR 2021 · Adversarial robustness and security › Certified and empirical robustness · approach: Attack evaluation and defense critique · 6 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
add RBF SVM (appropriate bandwidth) in place of CNNCNN · Symmetric CelebA/MNIST datasetsadversarial accuracy: CelebA Male: 0% -> 8%Improved
add RBF SVM in place of CNNCNN · Real CelebA Eyeglassesadversarial accuracy: 0.00% -> 32.3%Improved
add RBF SVM in place of CNNCNN · Real CelebA Bangsadversarial accuracy: 6.00% -> 24.7%Improved
add RBF SVM in place of Linear SVMLinear SVM · Real CelebA Smilingadversarial accuracy: 11.7% -> 16.3%Improved
train CNN on symmetric data instead of real data, test on real imagesCNN · CelebA Heavy Makeup test accuracytest accuracy: 86.3% -> 79.9%Hurt
train CNN on symmetric data instead of real data, test on real imagesCNN · CelebA Eyeglasses test accuracytest accuracy: 98.4% -> 91.7%Hurt
train CNN on symmetric data instead of real data, test on real imagesCNN · CelebA Smiling test accuracytest accuracy: 89.5% -> 85.6%Hurt
add more training examples to CNN (up to 1 million) (ablation)CNN · Symmetric datasetsadversarial robustness: up to 1 million examplesNo clear effect
increase CNN filters, layers, training iterations (ablation)CNN · Symmetric datasetsadversarial robustnessNo clear effect
add TRADES adversarial training to CNNCNN · Symmetric datasetsrobustness and accuracyMixed
use larger RBF bandwidth (ablation)RBF SVM · Symmetric datasetsadversarial robustnessHurt

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