AI Paper Atlas

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

Interpolation for Robust Learning: Data Augmentation on Wasserstein Geodesics

Jiacheng Zhu, Jielin Qiu, Aritra Guha, Zhuolin Yang, XuanLong Nguyen, Bo Li, Ding Zhao

ICML 2023 · Adversarial robustness and security › Certified and empirical robustness · approach: Adversarial training recipes · 3 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 worst-case Wasserstein-geodesic data augmentation and geodesic regularizationrobust training methods · CIFAR-10certified accuracyMixed
add worst-case Wasserstein-geodesic data augmentationempirical robustness training · CIFAR-100empirical robustness under FGSM: 16.8%Improved
add worst-case Wasserstein-geodesic data augmentationempirical robustness training · ImageNet (64×64)empirical robustness under FGSM: 16.8%Improved
add data augmentation and geodesic regularizationgradient-based adversarial training · empirical robustness experimentsℓ∞ robustnessImproved
increase augmentation batch size b_n (ablation)Wasserstein-geodesic augmentation · MNISTrobustnessImproved
increase augmentation sample size m_a (ablation)Wasserstein-geodesic augmentation · MNISTrobustnessImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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