Research map / Adversarial robustness and security / Certified and empirical robustness
Revisiting Adversarial Robustness Distillation from the Perspective of Robust Fairness
Xinli Yue, Ningping Mou, Qian Wang, Lingchen Zhao
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add class-wise re-weighting by LPS difficulty (Fair-ARD) | ARD, ResNet-18 · CIFAR-10 | AA worst-class robustness: 16.90 -> 29.20 | Improved |
| add class-wise re-weighting (Fair-IAD) | IAD, ResNet-18 · CIFAR-10 | AA worst-class robustness: 18.60 -> 25.60 | Improved |
| add class-wise re-weighting (Fair-RSLAD) | RSLAD, ResNet-18 · CIFAR-10 | AA worst-class robustness: 20.90 -> 25.10 | Improved |
| add class-wise re-weighting (Fair-MTARD) | MTARD, ResNet-18 · CIFAR-10 | AA worst-class robustness: 16.10 -> 22.60 | Improved |
| add class-wise re-weighting (Fair-MTARD) | MTARD, ResNet-18 · CIFAR-10 | clean average accuracy: 87.14 -> 81.98 | Hurt |
| add class-wise re-weighting (Fair-ARD) | ARD, ResNet-18 · CIFAR-10 | AA average robustness: 49.05 -> 49.13 | No clear effect |
| add class-wise re-weighting (Fair-ARD) | ARD, MobileNetV2 · CIFAR-10 | AA worst-class robustness: 18.60 -> 24.00 | Improved |
| add class-wise re-weighting (Fair-RSLAD) | RSLAD, MobileNetV2 · CIFAR-10 | AA worst-class robustness: 19.60 -> 26.30 | Improved |
| add example-wise GAIRAT re-weighting instead of class-wise (GAIR-ARD) | ARD, ResNet-18 · CIFAR-10 | AA average robustness: 49.05 -> 40.88 | Hurt |
| add FRL re-weighting instead of LPS (FRL-ARD) | ARD, ResNet-18 · CIFAR-10 | AA worst-class robustness: 16.90 -> 23.90 | Improved |
| add FAT fairness training instead of LPS (FAT-ARD) | ARD, ResNet-18 · CIFAR-10 | AA worst-class robustness: 16.90 -> 25.90 | Improved |
| add CFA re-weighting instead of LPS (CFA-ARD) | ARD, ResNet-18 · CIFAR-10 | AA worst-class robustness: 16.90 -> 20.00 | Improved |
Closest papers by meaning
- Improving Adversarial Robust Fairness via Anti-Bias Soft Label Distillation (NeurIPS 2024 · similarity 0.92)
- On the Alignment between Fairness and Accuracy: from the Perspective of Adversarial Robustness (ICML 2025 · similarity 0.91)
- DAFA: Distance-Aware Fair Adversarial Training (ICLR 2024 · similarity 0.89)
- Causal Adversarial Perturbations for Individual Fairness and Robustness in Heterogeneous Data Spaces (AAAI 2024 · similarity 0.89)
- Towards Fairness-Aware Adversarial Learning (CVPR 2024 · similarity 0.89)
- Out of Thin Air: Exploring Data-Free Adversarial Robustness Distillation (AAAI 2024 · similarity 0.88)
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.
