AI Paper Atlas

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

Self-Ensemble Protection: Training Checkpoints Are Good Data Protectors

Sizhe Chen, Geng Yuan, Xinwen Cheng, Yifan Gong, Minghai Qin, Yanzhi Wang, Xiaolin Huang

ICLR 2023 · Adversarial robustness and security › Certified and empirical robustness · approach: Augmentation and diffusion purification · 5 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
Use self-ensemble checkpoint gradients to craft protective perturbations instead of the single-model AdvPoison approach (ablation)CIFAR-10 protection, ResNet18 appropriator · CIFAR-10, ℓ∞=2/255testing accuracy: 41.35 -> 19.92Improved
Add feature alignment to SEP (ablation)SEP · CIFAR-10, ℓ∞=2/255, ResNet18 appropriatortesting accuracy: 19.92 -> 16.91Improved
Add variance reduction to SEP-FA (ablation)SEP-FA · CIFAR-10, ℓ∞=2/255, ResNet18 appropriatortesting accuracy: 16.91 -> 14.68Improved
Use self-ensemble checkpoints instead of training a conventional ensemble of 30 models (ablation)CIFAR-10 protection · CIFAR-10, ℓ∞=2/255, ResNet18 appropriatortesting accuracy: 16.32 -> 19.92Hurt
Add feature alignment to SEP (ablation)SEP · CIFAR-10, ℓ∞=2/255, VGG16 appropriatortesting accuracy: 28.12 -> 26.82Improved
Add variance reduction to SEP-FA (ablation)SEP-FA · CIFAR-10, ℓ∞=2/255, VGG16 appropriatortesting accuracy: 26.82 -> 23.66Improved
Increase the number of self-ensemble checkpoints from 30 to 120 (ablation)SEP · CIFAR-10testing accuracyNo clear effect
Use ℓ∞+ℓ0 perturbations instead of ℓ∞ perturbationsSEP-FA-VR under ℓ∞ adversarial training · CIFAR-10, ResNet18testing accuracy: 82.51 -> 13.19Mixed

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