Research map / Adversarial robustness and security / Certified and empirical robustness
Random Smoothing Might be Unable to Certify $\ell_\infty$ Robustness for High-Dimensional Images
Avrim Blum, Travis Dick, Naren Manoj, Hongyang Zhang
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 adversarial training with TRADES when training the Gaussian-smoothed base classifier | random smoothing with ResNet-110 · CIFAR-10 certified l_inf radius 2/255 | certified robust accuracy (%): 60.8% -> 62.6% | Improved |
| TRADES + random smoothing versus best prior baseline, natural accuracy | TRADES + Random Smoothing · CIFAR-10 natural accuracy | natural accuracy (%): 82.1% -> 78.8% | Hurt |
| scale input size 32 to 48 to 64 while keeping sigma/(sqrt(d) eps) constant (sigma 0.12, 0.18, 0.24) (ablation) | TRADES + random smoothing ResNet-110 · CIFAR-10 resized inputs, certified accuracy curves | certified accuracy vs l_inf radius | No clear effect |
Closest papers by meaning
- Mitigating the Curse of Dimensionality for Certified Robustness via Dual Randomized Smoothing (ICLR 2024 · similarity 0.90)
- Treatment of Statistical Estimation Problems in Randomized Smoothing for Adversarial Robustness (NeurIPS 2024 · similarity 0.90)
- Effects of Exponential Gaussian Distribution on (Double Sampling) Randomized Smoothing (ICML 2024 · similarity 0.89)
- Average Certified Radius is a Poor Metric for Randomized Smoothing (ICML 2025 · similarity 0.89)
- Provably Cost-Sensitive Adversarial Defense via Randomized Smoothing (ICML 2025 · similarity 0.88)
- Consistent Adversarially Robust Linear Classification: Non-Parametric Setting (ICML 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.
