AI Paper Atlas

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

Adversarial Coreset Selection for Efficient Robust Training

Hadi M. Dolatabadi, Sarah Erfani, Christopher A. Leckie

IJCV 2023 · Adversarial robustness and security › Certified and empirical robustness · approach: Adversarial training refinements · 11 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
train on adversarial coreset (GradMatch) instead of full dataTRADES · CIFAR-10 ResNet-18robust accuracy (%): 44.19 -> 41.52Hurt
train on adversarial coreset (Craig) instead of full dataL_inf-PGD · CIFAR-10 ResNet-18robust accuracy (%): 41.39 -> 45.07Improved
train on adversarial coreset (Craig) instead of full dataL2-PGD · SVHN ResNet-18robust accuracy (%): 53.02 -> 49.68Hurt
train on adversarial coreset (GradMatch) instead of full dataTRADES · CIFAR-10 WideResNet-28-10robust accuracy (%): 45.08 -> 47.83Improved
train on adversarial coreset (GradMatch) instead of full dataL_inf-PGD · ImageNet-100 ResNet-34robust accuracy (%): 40.52 -> 40.72No clear effect
train on adversarial coreset (GradMatch) instead of full dataTRADES · CIFAR-10 ResNet-18training time (mins): 344.29 -> 178.73Improved
train on adversarial coreset (Craig) instead of full dataTRADES · CIFAR-10 ResNet-18clean accuracy (%): 85.41 -> 83.03Hurt
add adversarial coreset selection to perceptual adversarial training (GradMatch)Fast-LPA PAT · ImageNet-12unseen robust accuracy (%): 53.23 -> 53.17No clear effect
add adversarial coreset selection (Craig) to Fast adversarial trainingFast AT · CIFAR-10training time (mins): 31.068 -> 16.695Improved
use only coreset samples rather than half coreset plus half clean (ablation)adversarial coreset (GradMatch) L_inf-PGD · CIFAR-10 ResNet-18robust accuracy (%): 40.05 -> 45.23Improved
use only coreset samples rather than half coreset plus half clean (ablation)adversarial coreset (GradMatch) L_inf-PGD · CIFAR-10 ResNet-18clean accuracy (%): 80.67 -> 84.31Hurt
use adversarial coreset selection instead of random data selection (ablation)adversarial GradMatch TRADES · CIFAR-10relative robust errorImproved

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