Research map / Adversarial robustness and security / Certified and empirical robustness
Dual Randomized Smoothing: Beyond Global Noise Variance
Chenhao Sun, Yuhao Mao, 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 |
|---|---|---|---|
| replace global sigma with input-dependent sigma from variance estimator (off-the-shelf classifier) | diffusion denoised smoothing · CIFAR-10 | certified accuracy (radius 1.0): 0.0 (sigma=0.25) / 19.34 (sigma=1.0) -> 19.85 at 1.0; but 86.61 -> 68.34 at radius 0 | Improved |
| use Dual RS instead of Multiscale (classifier fine-tuned) | Dual RS · CIFAR-10 | certified accuracy (radius 0.5): 39.15 -> 45.27 | Improved |
| use Dual RS instead of Multiscale | Dual RS · CIFAR-10 | certified accuracy (radius 0.0): 76.51 -> 70.53 | Hurt |
| use Dual RS instead of Multiscale | Dual RS · ImageNet | certified accuracy (radius 0.5): 55.8 -> 60.6 | Improved |
| use Dual RS instead of Multiscale | Dual RS · ImageNet | certified accuracy (radius 2.0): 25.2 -> 17.0 | Hurt |
| fine-tune the classifier under estimated variances (one round) (ablation) | Dual RS · CIFAR-10 | certified accuracy (radius 0.5): 41.28 -> 45.27 | Improved |
| use soft cross-entropy instead of standard CE for variance estimator (ablation) | Dual RS · CIFAR-10 | accuracy-radius curve | Improved |
| add consistency loss to variance estimator (ablation) | Dual RS · CIFAR-10 | accuracy-radius curve | Mixed |
| train variance estimator with much smaller N or train subset (ablation) | Dual RS · CIFAR-10 | certified accuracy | No clear effect |
| change variance estimator architecture (ablation) | Dual RS · CIFAR-10 | certified accuracy | No clear effect |
Closest papers by meaning
- 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 0.87)
- Robust Representation Consistency Model via Contrastive Denoising (ICLR 2025 · similarity 0.87)
- The Lipschitz-Variance-Margin Tradeoff for Enhanced Randomized Smoothing (ICLR 2024 · similarity 0.87)
- DRF: Improving Certified Robustness via Distributional Robustness Framework (AAAI 2024 · similarity 0.87)
- Treatment of Statistical Estimation Problems in Randomized Smoothing for Adversarial Robustness (NeurIPS 2024 · similarity 0.87)
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.
