AI Paper Atlas

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

Mitigating Adversarial Vulnerability through Causal Parameter Estimation by Adversarial Double Machine Learning

Byung-Kwan Lee, Junho Kim, Yong Man Ro

ICCV 2023 · Adversarial robustness and security › Certified and empirical robustness · approach: Attack evaluation and defense critique · 7 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 ADML fine-tuning to adversarial training defensesAT/TRADES/MART/AWP · CIFAR-10 AutoAttack (VGG-16)robust accuracy: 46.3 -> 54.5Improved
add ADML to AWPAWP · CIFAR-100 AutoAttack (WRN-70-10)robust accuracy: 30.0 -> 37.6Improved
add ADML to TransformersAT on ViT-S/16 · Tiny-ImageNet AutoAttackrobust accuracy: 31.8 -> 42.6Improved
add ADML to defenses on CIFAR-100/Tiny-ImageNetAT on VGG-16 · CIFAR-100 clean accuracyclean accuracy: 53.9 -> 52.2Hurt
add sample-splitting plus cross-fitting (ablation)ADML · CIFAR-10 AutoAttack (VGG-16)robust accuracy: 49.4 -> 54.4Improved
use only worst examples as treatments instead of worst and non-worst (ablation)ADML · CIFAR-10 AutoAttack (VGG-16)robust accuracy: 48.8 -> 54.4Improved
use non-worst examples only instead of worst only (ablation)ADML · CIFAR-10 AutoAttack (VGG-16)robust accuracy: 54.4 -> 45.8Hurt
add sample-splitting plus cross-fitting (ablation)ADML · Tiny-ImageNet AutoAttack (VGG-16)robust accuracy: 26.4 -> 32.2Improved
add ADML to TRADES with synthetic DDPM/EDM dataPORT/Gowal/HAT/SCORE/Wang · CIFAR-10 AutoAttackrobust accuracy: 60.6 -> 66.4Improved
add ADML to reduce class-wise vulnerabilityAT · bottom-k classes CIFAR-10relative causal parameter (%): rho_Avg 67.33 (ResNet-18)Improved

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