AI Paper Atlas

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

CIARD: Cyclic Iterative Adversarial Robustness Distillation

Liming Lu, Shuchao Pang, Xu Zheng, Xiang Gu, Anan Du, Yunhuai Liu, Yongbin Zhou

ICCV 2025 · Adversarial robustness and security › Certified and empirical robustness · approach: Adversarial training with feature consistency · 2 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 Iterative Teacher Training (ablation)CIARD (ResNet-18) · CIFAR-10PGD-TRADES robust accuracy: 53.84 -> 54.03Improved
add Iterative Teacher Training (ablation)CIARD (ResNet-18) · CIFAR-10clean accuracy: 87.76 -> 88.63Improved
add contrastive push loss on top of ITT (ablation)CIARD (ResNet-18) · CIFAR-10PGD-TRADES robust accuracy: 54.03 -> 54.54Improved
add contrastive push loss on top of ITT (ablation)CIARD (ResNet-18) · CIFAR-10clean accuracy: 88.63 -> 88.86Improved
add contrastive push loss on top of ITT (ablation)CIARD (ResNet-18) · CIFAR-10weighted accuracy: 71.30 -> 71.70Improved
CIARD vs B-MTARD dual-teacher methodResNet-18 · CIFAR-10 FGSMweighted robustness: 74.81 -> 75.38Improved
CIARD vs B-MTARD dual-teacher methodResNet-18 · CIFAR-100 PGD-SATrobust accuracy: 28.50 -> 28.05Hurt
CIARD vs B-MTARD dual-teacher methodMobileNet-V2 · CIFAR-100 FGSMweighted robustness: 50.25 -> 50.14Hurt
CIARD vs B-MTARD dual-teacher methodMobileNet-V2 · CIFAR-10 FGSMclean accuracy: 89.09 -> 89.51Improved
CIARD vs B-MTARD dual-teacher methodResNet-18 · CIFAR-10 Square Attackweighted robustness: 84.01 -> 84.45Improved

Later papers that compared with this method

1 later accepted paper reports CIARD as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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