Research map / Adversarial robustness and security / Black-box and transfer attacks
Understanding and Improving Ensemble Adversarial Defense
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 changed | Where | Measured | Effect |
|---|---|---|---|
| Add iGAT to ADP | ADP · CIFAR-10, PGD | accuracy (%): 39.63 -> 46.27 | Helped |
| Add iGAT to ADP | ADP · CIFAR-10, AutoAttack | accuracy (%): 35.53 -> 40.36 | Helped |
| Add iGAT to DVERGE | DVERGE · CIFAR-100, PGD | accuracy (%): 20.04 -> 23.20 | Helped |
| Add iGAT to DVERGE | DVERGE · CIFAR-100, AutoAttack | accuracy (%): 17.27 -> 18.59 | Helped |
| Add iGAT to SoE | SoE · CIFAR-10, natural images | accuracy (%): 82.19 -> 81.05 | Hurt |
| Assign global adversarial examples to the lowest-scoring base classifier (ablation) | iGAT_ADP · CIFAR-10, PGD | accuracy (%): 46.25 -> 41.31 | Hurt |
| Replace soft ranking-based distribution with uniform random assignment (ablation) | iGAT_ADP · CIFAR-10, PGD | accuracy (%): 46.25 -> 42.60 | Hurt |
| Replace soft probabilistic distribution with hard assignment (ablation) | iGAT_ADP · CIFAR-10, PGD | accuracy (%): 46.25 -> 44.21 | Hurt |
| Remove misclassification regularization (ablation) | iGAT_ADP · CIFAR-10, PGD | accuracy (%): 46.25 -> 42.32 | Hurt |
Closest papers by meaning
- Ensemble Adversarial Training: Attacks and Defenses (ICLR 2018 · similarity 0.91)
- Adversarial Defence by Diversified Simultaneous Training of Deep Ensembles (AAAI 2021 · similarity 0.90)
- Rethinking Model Ensemble in Transfer-based Adversarial Attacks (ICLR 2024 · similarity 0.87)
- Understanding Model Ensemble in Transferable Adversarial Attack (ICML 2025 · similarity 0.87)
- Ensemble Diversity Facilitates Adversarial Transferability (CVPR 2024 · similarity 0.87)
- On the Diversity of Adversarial Ensemble Learning (ICML 2025 · similarity 0.86)
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.