AI Paper Atlas

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

Generalization Bounds for Adversarial Contrastive Learning

Xin Zou, Weiwei Liu

JMLR 2023 · Adversarial robustness and security › Certified and empirical robustness · approach: Adversarial training refinements · 4 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 Frobenius-norm regularizer lambda=0.002 (ablation)adversarial contrastive learning (AERM) · CIFAR-10, PGD eps=0.01adversarial accuracy: 67.67 -> 69.25Improved
add Frobenius-norm regularizer lambda=0.002 (ablation)adversarial contrastive learning (AERM) · CIFAR-10, PGD eps=0.02adversarial accuracy: 46.71 -> 48.17Improved
add Frobenius-norm regularizer lambda=0.05 (ablation)adversarial contrastive learning (AERM) · CIFAR-10, FGSM eps=0.01adversarial accuracy: 67.28 -> 68.8Improved
add Frobenius-norm regularizer lambda=0.2 (ablation)adversarial contrastive learning (AERM) · CIFAR-10, FGSM eps=0.02adversarial accuracy: 45.93 -> 55.64Improved
add Frobenius-norm regularizer lambda=0.2 (ablation)adversarial contrastive learning (AERM) · CIFAR-10, FGSM eps=0.02clean accuracy: 54.28 -> 66.68Improved
add Frobenius-norm regularizer lambda=0.002 (ablation)adversarial contrastive learning (AERM) · CIFAR-10, PGD eps=0.01clean accuracy: 75.73 -> 74.8Hurt
add Frobenius-norm regularizer lambda=0.002 to 0.05 (ablation)adversarial contrastive learning (AERM) · CIFAR-10, FGSM eps=0.02adversarial accuracy: 45.93 -> 45.94No clear effect
increase block size from 1 to 10 (ablation)adversarial contrastive learning · CIFAR-10, PGD and FGSMadversarial accuracyImproved

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