AI Paper Atlas

Research map / Label-efficient and robust learning / Semi-supervised learning

Enhancing Adversarial Robustness in Low-Label Regime via Adaptively Weighted Regularization and Knowledge Distillation

Dongyoon Yang, Insung Kong, Yongdai Kim

ICCV 2023 · Label-efficient and robust learning › Semi-supervised learning · approach: GAN-based semi-supervised learning · 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
use SRST-AWR instead of RST and UAT++semi-supervised adversarial training · CIFAR-10 (4,000 labels)AutoAttack robust accuracy: 46.69 -> 51.72 (vs RST)Improved
replace supervised teacher with semi-supervised teacher (ablation)RST · CIFAR-10 (4,000 labels)AutoAttack robust accuracy: 46.69 -> 49.32Improved
replace supervised teacher with semi-supervised teacher (ablation)UAT++ · CIFAR-10 (4,000 labels)AutoAttack robust accuracy: 46.53 -> 48.46Improved
add adaptive weight w (AWR) instead of constant weight (TRADES-style) (ablation)SRST · CIFAR-10 (500 labels)AutoAttack robust accuracy: 43.93 -> 50.76Improved
add adaptive weight w (AWR) instead of constant weight (ablation)SRST · STL-10 (1,000 labels)AutoAttack robust accuracy: 63.41 -> 72.51Improved
add knowledge distillation with soft pseudo labels (ablation)SRST-AWR · CIFAR-10 (4,000 labels)AutoAttack robust accuracy: 50.02 -> 51.72Improved
add knowledge distillation with soft pseudo labels (ablation)SRST-AWR · CIFAR-10 (4,000 labels)standard accuracy: 84.37 -> 84.56No clear effect
use SRST-AWR instead of ARMOUREDsemi-supervised adversarial training · CIFAR-10 (WRN-28-2)PGD-7 robust accuracy: 55.12 -> 52.43Hurt
use SRST-AWR instead of ARMOUREDsemi-supervised adversarial training · SVHN (WRN-28-2)AutoAttack robust accuracy: 23.35 -> 78.21Improved
train SRST-AWR with 12% of labels versus supervised TRADES with 100% labelsSRST-AWR · CIFAR-10AutoAttack robust accuracy: 51.72 -> 51.88Improved
use AWR instead of TRADES with fully labeled datasupervised adversarial training · CIFAR-10 (fully labeled)AutoAttack robust accuracy: 51.72 -> 51.97Improved

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