AI Paper Atlas

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

AROID: Improving Adversarial Robustness Through Online Instance-Wise Data Augmentation

Lin Li, Jianing Qiu, Michael Spratling

IJCV 2024 · Adversarial robustness and security › Certified and empirical robustness · approach: Adversarial training refinements · 16 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 Vulnerability objective to policy learning (ablation)AROID · CIFAR-10 (PRN18)AutoAttack robustness: 49.95 -> 50.57Improved
add Affinity objective to policy learning (ablation)AROID · CIFAR-10 (PRN18)AutoAttack robustness: 49.41 -> 50.57Improved
add Diversity objective to policy learning (ablation)AROID · CIFAR-10 (PRN18)AutoAttack robustness: 22.47 -> 50.57Improved
add Diversity objective to policy learning (ablation)AROID · CIFAR-10 (PRN18)clean accuracy: 73.88 -> 84.68Improved
learn the augmentation policy instead of uniform sampling from the same space (ablation)AROID · CIFAR-10 (PRN18)AutoAttack robustness: 49.18 -> 50.57Improved
replace RandomCrop with AROID augmentationvanilla AT · CIFAR-10 (WRN34-10)AutoAttack robustness: 52.26 -> 55.91Improved
replace RandomCrop with AROID augmentationvanilla AT · CIFAR-10 (ViT-B/4)AutoAttack robustness: 46.72 -> 51.25Improved
replace RandomCrop with AROID augmentationvanilla AT · ImageNet (ConvNeXt-T)robust accuracy: 36.22 -> 40.40Improved
add AWP and SWA to AROIDAROID · CIFAR-10 (WRN34-10)AutoAttack robustness: 55.91 -> 57.03Improved
use offline transferred policy (AROID-T) instead of online AROIDAROID · CIFAR-10 (WRN34-10)AutoAttack robustness: 55.91 -> 55.61No clear effect
reduce policy update frequency, K from 5 to 20 (ablation)AROID · CIFAR-10 (PRN18)AutoAttack robustness: 50.57 -> 50.45No clear effect
enlarge the target model to WRN34-12 instead of using AROIDRandomCrop AT · CIFAR-10AutoAttack robustness: 52.26 -> 52.46No 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