AI Paper Atlas

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

Towards Robust Neural Networks via Random Self-ensemble

Xuanqing Liu, Minhao Cheng, Huan Zhang, Cho-Jui Hsieh

ECCV 2018 · Adversarial robustness and security › Certified and empirical robustness · approach: Attack evaluation and defense critique · 419 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 noise layers at training time as well as testing time (vs test noise only) (ablation)RSE · CIFAR-10 VGG16accuracy without attack: 20%Improved
add noise at test time with ensemble (vs noise only in training) (ablation)RSE · CIFAR-10 VGG16 under C&Waccuracy under weak attacksImproved
use 50-ensemble instead of 1-ensemble (ablation)RSE · CIFAR-10 VGG16 (c<0.4)accuracy under attack: ~8%Improved
use 50-ensemble instead of 1-ensemble under very strong attack (ablation)RSE · CIFAR-10 VGG16 (c>1.0)accuracy under attackHurt
increase number of ensemble models beyond 10 (ablation)RSE · CIFAR-10 VGG16clean test accuracyNo clear effect
add higher noise levels (init, inner) in training and testing (ablation)RSE · CIFAR-10 VGG16robustness vs weak-attack accuracyMixed
use RSE instead of Robust Opt+BReLURSE · CIFAR-10 VGG16, c=0.1accuracy under C&W: 20.69% -> 67.19%Improved
use RSE instead of no defenseVGG16 · CIFAR-10, c=0.03accuracy under C&W: 8.93% -> 86.06%Improved
use RSE instead of adversarial training (II)RSE · CIFAR-10 VGG16accuracy under C&WNo clear effect
use Robust Opt+BReLUVGG/Model A · STL10 Model Aaccuracy under C&WHurt

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