Research map / Adversarial robustness and security / Certified and empirical robustness
Boosting Randomized Smoothing with Variance Reduced Classifiers
Miklós Z. Horváth, Mark Niklas Mueller, Marc Fischer, Martin Vechev
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 |
|---|---|---|---|
| Average logits from an ensemble of classifiers rather than use one classifier | Randomized Smoothing classifiers · CIFAR10 and ImageNet | ACR: 5\% to 21\% | Improved |
| Increase ensemble size (ablation) | Randomized Smoothing classifiers · CIFAR10 | ACR | Improved |
| Use ensembles of 3–5 models rather than a single model (ablation) | Randomized Smoothing classifiers · CIFAR10 | ACR | Improved |
| Use 3 ResNet20 models instead of one ResNet110 (ablation) | Gaussian-trained Randomized Smoothing · CIFAR10 | ACR | Improved |
| Use 5 ResNet20 models instead of one ResNet110 (ablation) | Consistency-trained Randomized Smoothing · CIFAR10 | ACR | Improved |
| Increase perturbation samples for a single classifier instead of using an ensemble (ablation) | Randomized Smoothing classifier · CIFAR10 | ACR | Mixed |
| Combine classifiers trained with different methods (ablation) | Randomized Smoothing ensemble · CIFAR10 | ACR: up to 5\% | Improved |
| Use denoised classifiers in the ensemble (ablation) | Denoised Randomized Smoothing · CIFAR10 | ACR: up to 17\% | Improved |
| Apply adaptive sampling for predetermined certification radii | Randomized Smoothing certification · CIFAR10 | SampleRF: up to 55-fold | Improved |
| Use exponentially increasing adaptive-sampling phases, particularly 100, 1'000, 10'000, 120'000 (ablation) | CertifyAdp · CIFAR10 | SampleRF: 33.91 | Improved |
| Use K-Consensus with K=2 instead of full evaluation of a 10-model ensemble (ablation) | Consistency ResNet110 ensemble · CIFAR10, σ=0.25 | ACR: 0.546 -> 0.576 | Improved |
| Use K-Consensus with K=5 instead of full evaluation of a 10-model ensemble (ablation) | Consistency ResNet110 ensemble · CIFAR10, σ=0.25 | ACR: 0.583 -> 0.583 | No clear effect |
Closest papers by meaning
- The Lipschitz-Variance-Margin Tradeoff for Enhanced Randomized Smoothing (ICLR 2024 · similarity 0.89)
- Average Certified Radius is a Poor Metric for Randomized Smoothing (ICML 2025 · similarity 0.88)
- Mitigating the Curse of Dimensionality for Certified Robustness via Dual Randomized Smoothing (ICLR 2024 · similarity 0.88)
- Effects of Exponential Gaussian Distribution on (Double Sampling) Randomized Smoothing (ICML 2024 · similarity 0.88)
- Treatment of Statistical Estimation Problems in Randomized Smoothing for Adversarial Robustness (NeurIPS 2024 · similarity 0.87)
- DRF: Improving Certified Robustness via Distributional Robustness Framework (AAAI 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.
