AI Paper Atlas

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

Trade-Off Between Robustness and Accuracy of Vision Transformers

Yanxi Li, Chang Xu

CVPR 2023 · Adversarial robustness and security › Certified and empirical robustness · approach: Robustness-accuracy trade-off analysis · 22 citations (OpenAlex)

Read the paper

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
Replace single-adapter / head-only tuning with two adapters plus patch-level gated fusion (TORA-ViT) (ablation)ViT-B/16 frozen backbone · ImageNet-1K clean and PGD (λ=0.1)top-1 accuracy: clean 84.1 vs 82.5 (single adapter); PGD 23.3 vs 15.1Improved
Replace adapter-level AdapterFusion with patch-level trade-off-aware gated fusion (ablation)TORA-ViT · ImageNet-1K PGD (λ=0.9)top-1 accuracy: 57.5 vs 55.3Improved
Tune only a new classification head on frozen ViT (ablation)ViT-B/16 · ImageNet-1K PGD (λ=0.1)top-1 accuracy: 15.5 vs 23.3 for full modelHurt
Increase λ from 0.1 to 0.5 (more robustness weight)TORA-ViT-B/16 · ImageNet-1K clean vs PGDtop-1 accuracy: clean 84.1→83.7 (-0.4); PGD 23.3→38.0 (+14.7)Mixed
Increase λ from 0.5 to 0.9TORA-ViT-B/16 · ImageNet-Atop-1 accuracy: 39.2 → 22.2 (-17.0)Hurt
Increase λ from 0.5 to 0.9TORA-ViT-B/16 · ImageNet-1K FGSM and PGDtop-1 accuracy: FGSM 54.7→74.2; PGD 38.0→57.5Improved
Joint prediction of accuracy and robustness heads vs. single head at λ=0.5 (ablation)TORA-ViT-B/16 · ImageNet-1K cleantop-1 accuracy: joint 83.66 vs accuracy head 83.38 and robustness head 83.01; joint is lower-than-acc-head under PGD (37.99 vs 39.78)Mixed

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