AI Paper Atlas

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

Confound from All Sides, Distill with Resilience: Multi-Objective Adversarial Paths to Zero-Shot Robustness

Junhao Dong, Jiao Liu, Xinghua Qu, Yew-Soon Ong

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
use MOO-adversaries instead of untargeted adversaries (ablation)MOO-AD · ImageNet PGDrobust accuracy: 29.13 -> 36.58Improved
use MOO-adversaries instead of targeted adversaries (ablation)MOO-AD · ImageNet PGDrobust accuracy: 25.88 -> 36.58Improved
use MOO-adversaries instead of untargeted adversaries (ablation)MOO-AD · OOD datasets (SUN397, Flower102, CIFAR-100) PGDrobust accuracy: 16.87 -> 24.74Improved
use targeted instead of untargeted adversaries (ablation)MOO-AD · OOD datasets PGDrobust accuracy: 16.87 -> 20.59Improved
use targeted instead of untargeted adversaries (ablation)MOO-AD · ImageNet cleanaccuracy: 53.42 -> 50.94Hurt
increase number of MOO-adversaries from 1 to 10 (ablation)MOO-AD · 15-dataset average PGDrobust accuracy: 32.17 -> 35.70Improved
increase number of MOO-adversaries from 10 to 30 (ablation)MOO-AD · 15-dataset average PGDrobust accuracy: 35.70 -> 36.11No clear effect
increase trade-off factor beta (ablation)MOO-AD · 15-dataset averageclean vs robust accuracyMixed
add both MOPA and GDM components with MOO-adversaries (ablation)MOO-AD · 15-dataset averagePGD robust accuracy: 32.37 -> 35.70Improved
distill with MOO-AD instead of FAREViT-B student · 15-dataset average PGDrobust accuracy: 30.94 -> 35.70Improved
distill with MOO-AD instead of FAREViT-B student · 15-dataset average cleanaccuracy: 56.68 -> 58.96Improved
distill with MOO-AD instead of FARE at larger radius 4/255ViT-B student · 15-dataset average PGD eps 4/255robust accuracy: 12.42 -> 18.47Improved

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