AI Paper Atlas

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

Identifying Model Weakness with Adversarial Examiner

Michelle Shu, Chenxi Liu, Weichao Qiu, Alan Yuille

AAAI 2020 · Adversarial robustness and security › Certified and empirical robustness · approach: Attack evaluation and defense critique · 22 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
increase RL examination iterations from T=0 to T=500AlexNet · ShapeNet object classificationaverage post-softmax probability on true class: 63.98% -> 2.27%Hurt
increase BO examination iterations from T=0 to T=500AlexNet · ShapeNet object classificationaverage post-softmax probability on true class: 60.05% -> 25.43%Hurt
increase RL examination iterations from T=0 to T=500ResNet34 · ShapeNet object classificationaverage post-softmax probability on true class: 69.03% -> 13.13%Hurt
increase BO examination iterations from T=0 to T=500ResNet34 · ShapeNet object classificationaverage post-softmax probability on true class: 64.19% -> 45.55%Hurt
use BO instead of RL for the first 100 examination iterationsAlexNet · ShapeNet object classificationaverage post-softmax probability on true class: 65.91% -> 43.58%Hurt
use RL instead of BO after 500 examination iterationsAlexNet · ShapeNet object classificationaverage post-softmax probability on true class: 25.43% -> 2.27%Hurt
reduce training images per object from m=10 to m=1 (ablation)RL examiner with ResNet34 · ShapeNet object classification, T=200average model performance: 63.81% -> 18.92%Hurt
reduce training images per object from m=10 to m=1 (ablation)BO examiner with ResNet34 · ShapeNet object classification, T=200average model performance: 49.79% -> 10.92%Hurt
reorder the nine sampled rendering factors (ablation)RL examiner · ShapeNet object classification, lamp examplesconvergence to identified weaknessesNo clear effect
flip the objective from maximizing loss to minimizing loss (ablation)Adversarial examiner · ShapeNet piano instancepost-softmax probability on true classImproved

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