Research map / Label-efficient and robust learning / Recognition and long-tail
Certifying Confidence via Randomized Smoothing
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 |
|---|---|---|---|
| use CDF-based certificate instead of naive Gaussian-mean bound (ablation) | smoothed classifier confidence certificate · CIFAR-10 and ImageNet, sigma=0.25 | certified accuracy at a confidence threshold | Helped |
| use margin instead of average prediction score as confidence measure (threshold zero) (ablation) | CDF certificate · CIFAR-10 and ImageNet | certified accuracy | Helped |
| use CDF certificate vs best-possible naive baseline (empirical mean instead of Hoeffding bound) (ablation) | CDF certificate · CIFAR-10 ResNet-110 | certified accuracy | Helped |
| standard certified radius used as proxy for confidence | Gaussian smoothing · CIFAR-10 and ImageNet, sigma=0.25 | correlation of certified radius with softmax score | No clear effect |
Closest papers by meaning
- The Lipschitz-Variance-Margin Tradeoff for Enhanced Randomized Smoothing (ICLR 2024 · similarity 0.92)
- Mitigating the Curse of Dimensionality for Certified Robustness via Dual Randomized Smoothing (ICLR 2024 · similarity 0.90)
- Average Certified Radius is a Poor Metric for Randomized Smoothing (ICML 2025 · similarity 0.89)
- Towards Large Certified Radius in Randomized Smoothing Using Quasiconcave Optimization (AAAI 2024 · similarity 0.88)
- Effects of Exponential Gaussian Distribution on (Double Sampling) Randomized Smoothing (ICML 2024 · similarity 0.88)
- Incremental Randomized Smoothing Certification (ICLR 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.