Research map / Label-efficient and robust learning / Recognition and long-tail
Understanding Intrinsic Robustness Using Label Uncertainty
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 a label uncertainty constraint to concentration estimation | Intrinsic robustness estimation on CIFAR-10 · CIFAR-10, ℓ∞ ε=8/255 | intrinsic robustness estimate: 90% -> about 82% | Helped |
| Abstain on the 2% most uncertain examples | Adversarially-trained CIFAR-10 classifier · CIFAR-10, ℓ∞ ε=8/255 | clean accuracy: 89.7% to 90.3% | Helped |
| Abstain on the 2% most uncertain examples | Adversarially-trained CIFAR-10 classifier · CIFAR-10, ℓ∞ ε=8/255 | robust accuracy: 59.5% to 60.4% | Helped |
Closest papers by meaning
- Empirically Measuring Concentration: Fundamental Limits on Intrinsic Robustness (NeurIPS 2019 · similarity 0.90)
- Adversarial Examples Might be Avoidable: The Role of Data Concentration in Adversarial Robustness (NeurIPS 2023 · similarity 0.89)
- Improved Estimation of Concentration Under $\ell_p$-Norm Distance Metrics Using Half Spaces (ICLR 2021 · similarity 0.89)
- Probably Approximately Global Robustness Certification (ICML 2025 · similarity 0.87)
- Soften to Defend: Towards Adversarial Robustness via Self-Guided Label Refinement (CVPR 2024 · similarity 0.87)
- SURE: SUrvey REcipes for building reliable and robust deep networks (CVPR 2024 · 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.